train.json

[
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Hong Z., Guo S., Li P., Chen W.\nPyramid: A layered sharding blockchain system\nIEEE INFOCOM 2021-IEEE Conference on Computer Communications, IEEE (2021), pp. 1-10 \nAbstract: Sharding can significantly improve the blockchain scalability, by dividing nodes into small groups called shards that can handle transactions in parallel. However, all existing sharding systems adopt complete sharding, i.e., shards are isolated. It raises additional overhead to guarantee the atomicity and consistency of cross-shard transactions and seriously degrades the sharding performance. In this paper, we present Pyramid, the first layered sharding blockchain system, in which some shards can store the full records of multiple shards thus the cross-shard transactions can be processed and validated in these shards internally. When committing cross-shard transactions, to achieve consistency among the related shards, a layered sharding consensus based on the collaboration among several shards is presented. Compared with complete sharding in which each cross-shard transaction is split into multiple sub-transactions and cost multiple consensus rounds to commit, the layered sharding consensus can commit cross-shard transactions in one round. Furthermore, the security, scalability, and performance of layered sharding with different sharding structures are theoretically analyzed. Finally, we implement a prototype for Pyramid and its evaluation results illustrate that compared with the stateof-the-art complete sharding systems, Pyramid can improve the transaction throughput by 2.95 times in a system with 17 shards and 3500 nodes.",
        "output": "Hong et al. (2021) introduced a hierarchical system structure that allows specific nodes in two shards related to cross-shard transactions to store the states of both shards, thereby converting cross-shard transactions into intra-shard transactions. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Latt, W.T.; Newton, R.C.; Visentini-Scarzanella, M.; Payne, C.J.; Noonan, D.P.; Shang, J.; Yang, G.-Z. A Hand-held instrument to maintain steady tissue contact during probe-based confocal laser endomicroscopy. IEEE Trans. Biomed. Eng. 2011, 58, 2694\u20132703. \nAbstract: Probe-based confocal laser endomicroscopy (pCLE) provides high-resolution in vivo imaging for intraoperative tissue characterization. Maintaining a desired contact force between target tissue and the pCLE probe is important for image consistency, allowing large area surveillance to be performed. A hand-held instrument that can provide a predetermined contact force to obtain consistent images has been developed. The main components of the instrument include a linear voice coil actuator, a donut load-cell, and a pCLE probe. In this paper, detailed mechanical design of the instrument is presented and system level modeling of closed-loop force control of the actuator is provided. The performance of the instrument has been evaluated in bench tests as well as in hand-held experiments. Results demonstrate that the instrument ensures a consistent predetermined contact force between pCLE probe tip and tissue. Furthermore, it compensates for both simulated physiological movement of the tissue and involuntary movements of the operator's hand. Using pCLE video feature tracking of large colonic crypts within the mucosal surface, the steadiness of the tissue images obtained using the instrument force control is demonstrated by confirming minimal crypt translation.",
        "output": "Latt et al. (2011) developed a hand-held device with force control to maintain stable probe\u2013tissue contact and used it for porcine rectal imaging in anal endoscopic microsurgery. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Tang, M.; Rong, Y.; Zhou, J.; Li, X.R. Invariant Adaptive Detection of Range-Spread Targets Under Structured Noise Covariance. IEEE Trans. Signal Process. 2017, 65, 3048\u20133061. \nAbstract: The invariance principle is adopted to develop an exhaustive study for adaptive detection of range-spread targets in Gaussian noise sharing a block-diagonal covariance structure. For this problem, the usual generalized likelihood ratio principle is intractable. In this paper, we first determine the largest group of affine transformations that does not alter the decision problem. Then, a maximal invariant identified by this group is derived, which can characterize the totality of the invariant detectors and extends the existing results for the point-target case. A theoretical performance analysis of the maximal invariant is also given. Finally, we propose two classes of invariant detectors, which are distinguished by whether a constant false alarm rate (CFAR) is maintained. Numerical experiments are provided for a comparison of the proposed detectors, where a tradeoff between the CFARness and the improved performance has been observed and studied.",
        "output": "Tang et al. (2017) extensively investigated the adaptive detection of range-spread targets with noise covariance sharing block-diagonal structures, and proposed two categories of invariant detectors through adopting the invariance principle.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Shu, H.; Yu, Q.; Niu, C.; Sun, D.; Wang, Q. The coupling effects of wet-dry and freeze\u2013thaw cycles on the mechanical properties of saline soil synergistically solidified with sulfur-free lignin, basalt fiber and hydrophobic polymer. Catena 2024, 238, 107832. \nAbstract: Saline soil in semi-arid and seasonally frozen areas is highly susceptible to periodic evaporative freezing and thawing, leading to impacts on the physical properties and structure of the soil. This can have a significantly negative impact on engineering construction. Renewable and environmentally friendly composite materials (sulfur-free lignin, basalt fiber and hydrophobic polymer) were proposed to improve the physicochemical properties of saline soil. Based on the periodic changes in water and temperature in these regions, the coupling effects of wet-dry and freeze\u2013thaw (WDFT) on saline soil was simulated by the experimental setup; consolidated undrained triaxial compression tests were carried out to further investigate the changing pattern of the strength characteristics of the untreated soil and the composite solidified soil. The results show that WDFT cycles have a deterioration effect on the mechanical properties of the soil; the deterioration stage mainly occurs in the first five cycles, while the trend of strength deterioration slows down after 10 cycles. The composite solidified material can significantly improve the strength of the saline soil, compared with the untreated soil. The rate of strength increase can reach up to 85.27% and the residual ratio of the failure strength is higher than that of the untreated soil. It also has a high resistance to coupling deterioration, with the solidification effect coefficient of the composite solidified soil being greater than 1 for different WDFT cycles. In addition, based on the hyperbolic model parameter fitting method, the effects of WDFT cycles and the confining pressure on the corresponding parameters were analyzed and the corresponding expressions were established. The stress\u2013strain relationship can be better predicted by adopting the ultimate deviatoric stress \u03c3 1-\u03c3 3 ult as the normalization factor.",
        "output": "Shu et al. (2024) examined the mechanical properties of salt-affected soil co-cured with sulfur-free lignin, basalt fiber, and hydrophobic polymers, observing heightened resistance to degradation from dry\u2013wet cycles.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "K\u00f6hne, J.M.; Mohanty, B.P. Water flow processes in a soil column with a cylindrical macropore: Experiment and hierarchical modeling. Water Resour. Res. 2005, 41, W03010. \nAbstract: Physically based models are increasingly applied to analyze contaminant transport in soil by preferential water flow. Unfortunately, in the past, preferential flow models were rarely evaluated using appropriate experimental data because of the complexity of conceptual models and limitations of measuring techniques. In this study, we designed a novel soil column experiment with advanced measurement techniques that enabled us to discriminate macropore and matrix water flow and quantify interdomain (macropore\u2010matrix) water transfer. Experiments of drainage and upward and downward infiltration revealed hydraulic nonequilibrium between matrix and macropore domains. Cumulative interdomain water transfer could be estimated using mass balance calculations. In a hierarchical modeling approach, four numerical models of different complexity were compared to the column experiment data. As a reference model, pseudo three\u2010dimensional axisymmetric Richards' equation (ARE) was used for inverse estimation of domain\u2010specific hydraulic parameters. The parameters were subsequently used for performance evaluation of an equivalent continuum model with bimodal hydraulic functions (ECM) and two dual\u2010permeability models with first\u2010order (DPM1) and second\u2010order (DPM2) terms for water transfer between macropore and matrix. Overall, DPM2 gave slightly more accurate domain\u2010specific results of water flow, water contents, and pressure heads than DPM1. Although bulk soil water flow results for the ECM were least accurate, they were considered to be within acceptable range. Compared to the more comprehensive ARE approach, DPMs were found to be almost equally capable of simulating interdomain and intradomain water flow and could be considered more versatile as they allow for a variety of macropore\u2010matrix geometries.",
        "output": "K\u00f6hne and Mohanty (2005) used HYDRUS2D software to simulate the circular-macropore flow in a soil column and found that the velocity of macropore flow was hundreds of times higher than that of matrix flow.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Alaoui, A. Modelling susceptibility of grassland soil to macropore flow. J. Hydrol. 2015, 525, 536\u2013546. \nAbstract: Investigating preferential flow, including macropore flow, is crucial to predicting and preventing point sources of contamination in soil, for example in the vicinity of pumping wells. With a view to advancing groundwater protection, this study aimed (i) to quantify the strength of macropore flow in four representative natural grassland soils on the Swiss plateau, and (ii) to define the parameters that significantly control macropore flow in grassland soil. For each soil type we selected three measurement points on which three successive irrigation experiments were carried out, resulting in a total of 36 irrigations. The strength of macropore flow, parameterized as the cumulated water volume flowing from macropores at a depth of 1 m in response to an irrigation of 60 mm h\u22121 intensity and 1 h duration, was simulated using the dual-permeability MACRO model. The model calibration was based on the key soil parameters and fine measurements of water content at different depths. Modelling results indicate high performance of macropore flow in all investigated soil types except in gleysols. The volume of water that flowed from macropores and was hence expected to reach groundwater varied between 81% and 94% in brown soils, 59% and 67% in para-brown soils, 43% and 56% in acid brown soils, and 22% and 35% in gleysols. These results show that spreading pesticides and herbicides in pumping well protection zones poses a high risk of contamination and must be strictly prohibited. We also found that organic carbon content was not correlated with the strength of macropore flow, probably due to its very weak variation in our study, while saturated water content showed a negative correlation with macropore flow. The correlation between saturated hydraulic conductivity (Ks) and macropore flow was negative as well, but weak. Macropore flow appears to be controlled by the interaction between the bulk density of the uppermost topsoil layer (0\u20130.10 m) and the macroporosity of the soil below. This interaction also affects the variations in Ks and saturated water content. Further investigations are needed to better understand the combined effect of all these processes including the exchange between micropore and macropore domains.",
        "output": "Alaoui (2015) simulated the macropore flow using the dual-permeability MACRO model and manifested that the volume of water that flowed from macropores and was expected to reach groundwater varied between 81% and 94% in brown soils.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Lee, J.; Madanat, S. Optimal policies for greenhouse gas emission minimization under multiple agency budget constraints in pavement management. Transp. Res. Part D 2017, 55, 39\u201350.  \nAbstract: Greenhouse gas emissions reduction has garnered special importance in recent times in the transportation sector, including pavement design and management. In this study, we incorporate this environmental objective in pavement management. We present an optimization problem to minimize GHG emissions under multiple budget constraints by determining joint management strategies for a range of heterogeneous interventions, including maintenance, rehabilitation and reconstruction. We propose a computationally efficient bottom-up solution algorithm, which is built on Lagrangian Relaxation and Dynamic Programming. Finally, we apply our findings to a real-world highway network in California, where the results show a potential GHG emissions reduction of 20% through an increased combined budget of 35% on the Pareto frontier.",
        "output": "Lee et al. (2017) discussed the optimal pavement management strategy to reduce greenhouse gas emissions under budget constraints, constructed an optimization model considering budget constraints and minimizing greenhouse gas emissions, and designed a solution algorithm based on Lagrangian relaxation and dynamic programming.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Navin, M. S., and Agilandeeswari, L. (2020). Comprehensive review on land use/land cover change classification in remote sensing. J. Spe. Im 9, 1\u201321. doi:10.1255/jsi.2020.a8 \nAbstract: Analysing multispectral (MSP) and hyperspectral (HSP) satellite images in the field of remote sensing and the geographic information system (GIS) environment have become some of the hottest topics among researchers around the world. Everyday changes on the Earth\u2019s surface have a significant impact on society, and this has been the driver for researchers to work on the land use/land cover (LU/LC) change problem. The information gathered from various satellites has been used by researchers to map the Earth\u2019s features and infrastructures. Land use and land cover are two different terms to describe the Earth\u2019s surface. The land cover area represents the forest-covered areas, wetlands, grasslands, water-covered areas, mountainous regions and deserts etc. Specific events and changes that take place in land cover represent changes in land use categories, such as urbanisation, shopping centres, reservoirs and parks etc.  Observing the specific LU/LC changes that take place on the Earth\u2019s surface has been a significant problem for researchers. Time series satellite images have been acquired and analysed through various stages of LU/LC, namely pre-processing, classification and prediction, to solve the LU/LC change detection problem. ",
        "output": "According to Navin and Agilandeeswari (2020) the outcome of LULC mapping results is influenced not only by the suitability of the imagery but also by the careful selection of the classification methods. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "H. Wu, B.B. He, B.C. Chen, A. Liu Toxicity of polyvinyl chloride microplastics on Brassica rapa Envrion. Pollut., 336 (2023), Article 122435 \nAbstract: Microplastics (MPs) can pose high risk to living organisms due to their very small sizes. This study selected polyvinyl chloride MPs (PVC-MPs) which experienced up to 1000 h UV light radiation to investigate the influence of PVC-MPs on Brassica rapa growth. The outcomes showed the presence of PVC-MPs inhibited the plants' growth. The stem length, root length, fresh weight and dry weight of plants exposed to PVC-MPs after 30 days reduced by 45.9%, 35.2%, 26.1% and 5.2%, respectively. The chlorophyll, soluble sugar, malondialdehyde (MDA) and catalase (CAT) concentrations for plants exposed to PVC-MPs after 30 days increased by 25.9%, 135.7%, 88.7% and 47.1% respectively. It was also observed that PVC-MPs blocked the plants' leaf stomata and even entered plants' bodies. This might lead to PVC-MPs movement within the plants and influence plants' growth. The transcriptomic analysis results indicated that exposure to PVC-MPs up-regulated metabolic pathway of plant hormone signal transduction of the plants and down-regulated pathway network of ribosome. However, the research outcomes also showed that the PVC-MPs\u2019 locations in soil (located at the upper layers or at lower layers) and the UV light radiation time did not exert significantly different influences on inhibiting plants' growth. This can be attributed to PVC-MPs\u2019 small sizes and not much decomposition under light radiation. These imply that longer light radiation time and different particle sizes should be included into future research in order to further explore photodegraded MPs\u2019 toxicity effects on plants.",
        "output": "Wu et al. (2023) compared the toxicity of original and photodegraded polyvinyl chloride (PVC) on Brassic rapa. They found that compared to original PVC, photodegraded PVC more inhibited plants growth and blocked leaf stomata, hence negatively influencing photosynthesis.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Cui, L.J.; Zhang, M.; Guo, S.R.; Cao, Y.L.; Zeng, W.H.; Li, X.L.; Zheng, B. Multi-objective numerical simulation of geometrical characteristics of laser cladding of cobalt-based alloy based on response surface methodology. Meas. Control 2021, 54, 1125\u20131135. \nAbstract: The objectives of this study are to optimize the key process parameters of laser cladding remanufacturing parts, improve the sealing quality of the hemispherical valve and prolong and improve its service life and reliability. A high-power fiber-coupled semiconductor laser was used to fabricate a single Co-based alloy cladding layer on the pump valve material ZG45 plate. The key process parameters of laser power, scanning speed and powder feeding rate in the process of laser remanufacturing are taken as optimization variables, and the coating width, coating height, coating depth, aspect ratio and dilution rate are taken as response indexes. Based on the response surface analysis method, the central compound experiment is designed using Design-Expert software. The variance analysis of the experimental results is performed, and the regression prediction model of the process parameters relative to the corresponding index is established. Through analysis of the established perturbation diagram and three-dimensional response surface, it is concluded that the main influence factors of melting width and penetration depth are laser power and positive effect, and the main influence factors of melting height are scanning speed and negative effect. The average error of each regression prediction model is lower than 10%. The above research work has important guiding significance for optimizing the process parameters and improving the cladding quality of cobalt-based alloy on ZG45.",
        "output": "Cui et al. (2021) utilized laser cladding technology to fabricate cobalt-based alloy coatings on ZG45 plates, established a regression prediction model of process parameters and evaluation indexes based on experimental results, and analyzed the main influencing factors of cladding quality through the response surface method.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Balaskas, S.; Panagiorarou, A.; Rigou, M. Impact of environmental concern, emotional appeals, and attitude toward the advertisement on the intention to buy green products: The case of younger consumer audiences. Sustainability 2023, 15, 13204. \nAbstract: The protection of our natural environment and the rational use of our natural resources are topics that have gained enormous attention the last years, with thousands of people changing their buying behaviors and making more environmentally conscious purchase decisions. Green consumer behavior is concerned with environmental issues or societal considerations that are reflected in purchase decisions. In this article, we study the factors influencing the intention of consumers to buy green products by proposing and validating a research model depicting the dependencies of green purchase intention from the selected factors. More specifically, the aim of the exploratory study is to investigate the impact of positive and negative emotions on individuals\u2019 perceptions of environmentally friendly products and services, as well as the influence of attitudes toward green ads and of consumers\u2019 environmental concerns on green purchasing behavior. The study was conducted with 75 participants who were shown six ads promoting a specific ecofriendly product, with each ad featuring a different emotional appeal both through its visual imagery and its textual information; three of the ads elicited negative emotions (fear, guilt, and disgust) and three positive emotions (joy, interest/curiosity, and inspiration). Findings indicate that ads that elicit negative emotions demonstrate a significant positive effect on consumers\u2019 attitudes toward the green ad and on their intention to buy the promoted green product, but this does not apply to ads that elicit positive emotions. The statistical analysis also revealed that the attitudes toward the green ad are not a significant predictor of consumers\u2019 buying intention. Moreover, as expected, consumers with high environmental concern demonstrate stronger intention to buy the promoted green product compared to consumers with low environmental concern.",
        "output": "Balaskas et al. (2023)  indicate that one of the motivations for consumers to purchase green products is to make up for past unethical behavior, restore their image, and regain self-affirmation.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Cho, S.; Lee, H.; Chung, W. Strengthening Effect of Prestressed Near-Surface Mounted CFRP Bar System According to Material Properties of Aged Reinforced Concrete Beams. Compos. Struct. 2022, 282, 115121. \nAbstract: The flexural performance improvement of age-deteriorated reinforced concrete (RC) beams by a near-surface mounted carbon fiber-reinforced polymer (NSM CFRP) bar system was experimentally investigated. Ten 6.4 m long RC beams were fabricated and tested in four-point bending using different concrete compressive strengths to distinguish between old and new concrete, different steel reinforcement ratios to reflect deterioration with age, and different quantities of prestressed and non-prestressed CFRP bars. The results indicated that the ultimate strengths of the NSM CFRP-strengthened RC beams were up to twice that of the un-strengthened control beam, and the strengthening effect increased with the material properties of the RC beam. A finite element model of the strengthened RC beam was constructed and verified against the experimental results, then used to conduct a parametric study of the influence of the concrete compressive strength and steel reinforcement ratio on the strengthening effect of the prestressed NSM CFRP bar system.",
        "output": "A finite element (FE) model was used by Cho et al. (2022) to conduct a parametric study. The model precision was validated using test outcomes. The errors of the cracking, yielding and ultimate loads between the numerical and experimental results were within 9%.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Mosley, M.P. Streamflow Generation in a Forested Watershed, New Zealand. Water Resour. Res. 1979, 15, 795\u2013806. \nAbstract: A 0.3028\u2010ha watershed has been instrumented to monitor streamflow and subsurface flow through the soil mantle at a variety of topographic locations. The watershed is forested, with steep (35\u00b0) slopes and shallow (average 55 cm) soils on impermeable Old Man gravels. Data for a number of storms indicate that subsurface flow via \u2018macropores\u2019 (root channels, pipes) and seepage zones in the soil is the predominant mechanism of channel stormflow generation in storms with quickflows greater than about 1 mm. Subsurface flow from all parts of the watershed appears to contribute to stormflow even in very small storms (quickflow of the order of 3% of net precipitation). The saturated hydraulic conductivity of the soil matrix is not a limiting factor on the ability of subsurface flow to generate channel stormflow, because dye tracer experiments demonstrate that water may move through macropores (particularly root channels) at rates 2 orders of magnitude greater. However, subsurface flow from lower slope areas contributes to delayed flow; cessation of subsurface flow and Streamflow after a drought period is roughly coincident in time. In the study area it appears that streamflow is at almost all times dominated by subsurface flow and that runoff from partial and variable source areas contributes significant quantities of streamflow only during the rising limb of small (less than 1 mm of quickflow) flood hydrographs.",
        "output": "Mosley (1979) analyzed a large amount of rainfall data and concluded that macropore flow is the main mechanism for the formation of channel stormflow, and water could move through macropores (mainly root channels) at a rate twice the infiltration rate of the soil.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "De Maio, A. Polarimetric adaptive detection of range-distributed targets. IEEE Trans. Signal Process. 2002, 50, 2152\u20132159. \nAbstract: We address the problem of polarimetric adaptive detection of range-spread targets in Gaussian noise with unknown covariance matrix. At the design stage, we model the target echo from each polarimetric channel as a deterministic signal known up to a scaling factor (possibly varying from cell to cell), which accounts for the polarimetric scattering properties of the target. We first show the failure of the generalized likelihood ratio test (GLRT) procedure to deal with this kind of problem, and thus, we propose a fully adaptive detector based on the method of sieves. We also derive the analytical expression for the probability of false alarm and show that the newly introduced receiver can be made bounded constant false alarm rate (CFAR). Finally, we present simulation results highlighting the performance gain that can be achieved by resorting to polarization diversity in conjunction with high resolution.",
        "output": "In terms of adaptive detection, DeMaio (2002) addressed the problem related to the polarimetric adaptive detection of range-spread targets with an unknown covariance matrix.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Kodepogu, K.; Manjeti, V.B.; Siriki, A.B. Machine Learning for Road Accident Severity Prediction. Mechatron. Intell Transp. Syst. 2023, 2, 211\u2013226. \nAbstract: In the realm of road safety management, the development of predictive models to estimate the severity of road accidents is paramount. This study focuses on the multifaceted nature of factors influencing accident severity, encompassing both vehicular attributes such as speed and size, and road characteristics like design and traffic volume. Additionally, the impact of variables, including driver demographics, experience, and external conditions such as weather, are considered. Recent advancements in data analysis and machine learning (ML) techniques have directed attention toward their application in predicting traffic accident severity. Unlike traditional statistical methods, ML models are adept at capturing complex variable interactions, thereby offering enhanced prediction accuracy. However, the efficacy of these models is intrinsically tied to the quality and comprehensiveness of the utilized data. This research underscores the imperative of uniform data collection and reporting methodologies. Through a meticulous analysis of existing literature, the paper delineates the foundational concepts, theoretical frameworks, and data sources prevalent in the field. The findings advocate for the continuous development and refinement of sophisticated models, aiming to diminish the frequency and gravity of road accidents. Such efforts contribute significantly to the enhancement of traffic control and public safety measures.",
        "output": "Kodapogu et al. (2023) utilized machine learning techniques to predict the severity of road accidents, demonstrating the potential of computational tools in enhancing traffic safety proactively.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Berkovic, S.; Yezioro, A.; Bitan, A. Study of Thermal Comfort in Courtyards in a Hot Arid Climate. Sol. Energy 2012, 86, 1173\u20131186.  \nAbstract: The outdoor thermal comfort in an enclosed courtyard has been studied numerically by the three dimensional prognostic microclimate model, Envi-met 3.1. The effect of wind, and shading by different means \u2013 galleries, horizontal shading or trees \u2013 has been examined. The effect of wind is evaluated by allowing cross-ventilation through openings at 3 and 5m height above ground level, designed according to the prevalent wind direction. The study was conducted for the hours 11\u201317 LT during June assuming average climate conditions. The thermal comfort is evaluated by the Predicted Mean Vote (PMV) index. During hot summer days, outdoor comfort is mainly dependent on solar radiation; hence, shading is the best means to improve comfort, while the contribution of wind under all configurations studied was limited and much smaller than the shade contribution. The amount of shade is mainly determined by the courtyard orientation. Inspection of empty enclosed courtyards has shown that an elongated E\u2013W rectangular courtyard has the least shade, and therefore it is the most uncomfortable. When the courtyard is ventilated by openings, hot air and radiation penetrate through them increasing the air temperature and the radiation temperature in the courtyard relative to the conditions obtained in a closed courtyard. Higher openings are less comfortable to stay under, and further decrease the comfort in the courtyard. The addition of trees or/and galleries to the closed courtyard significantly improves the outdoor comfort. Under the assumption of constant building temperature of 25\u00b0, the addition of galleries is the most efficient shading strategy. Quantitative results exhibiting these trends are presented for specific configurations and orientations of ventilated and/or shaded courtyards.",
        "output": "Berkovic et al. (2012) further explored the impact of various shading strategies on courtyard thermal comfort, noting the significant roles of wind speed and shading in enhancing thermal comfort.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Li C., Huang H., Zhao Y., Peng X., Yang R., Zheng Z., Guo S. Achieving scalability and load balance across blockchain shards for state sharding 2022 41st International Symposium on Reliable Distributed Systems, SRDS, IEEE (2022), pp. 284-294 \nAbstract: Sharding technique is viewed as the most promising solution to improving blockchain scalability. However, to implement a sharded blockchain, developers have to address two major challenges. The first challenge is that the ratio of cross-shard transactions (TXs) across blockchain shards is very high. This issue significantly degrades the throughput of a blockchain. The second challenge is that the workloads across blockchain shards are largely imbalanced. If workloads are imbalanced, some shards have to handle an overwhelming number of TXs and become congested very possibly. Facing these two challenges, a dilemma is that it is difficult to guarantee a low cross-shard TX ratio and maintain the workload balance across all shards, simultaneously. We believe that a fine-grained account-allocation strategy can address this dilemma. To this end, we first formulate the tradeoff between such two metrics as a network-partition problem. We then solve this problem using a community-aware account partition algorithm. Furthermore, we also propose a sharding protocol, named Transformers, to apply the proposed algorithm into the sharded blockchain system. Finally, trace-driven evaluation results demonstrate that the proposed protocol outperforms other baselines in terms of throughput, latency, cross-shard TX ratio, and the queue size of transaction pool.",
        "output": "Subsequently, Li et al. (2022) proposed a community sharding algorithm named CLPA. The core of CLPA lies in iteratively updating the relationships between transactions by assigning them labels. This method effectively reduces the cross-shard ratio and achieves load balancing. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Kan, H.Y.; Li, C.; Wang, Z.Q. An Integrated Convolutional Neural Network-Bidirectional Long Short-Term Memory-Attention Mechanism Model for Enhanced Highway Traffic Flow Prediction. J. Urban Dev. Manag. 2024, 3, 18\u201333.  \nAbstract: The burgeoning expansion of the Internet of Things (IoT) technology has propelled Intelligent Traffic Systems (ITS) to the forefront of IoT applications, with accurate highway traffic flow prediction models playing a pivotal role in their development. Such models are essential for mitigating highway traffic congestion, reducing accident rates, and informing city planning and traffic management strategies. Given the inherent periodicity, nonlinearity, and variability of highway traffic data, an innovative model leveraging a Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention Mechanism (AM) is proposed. In this model, feature extraction is accomplished via the CNN, which subsequently feeds into the BiLSTM for processing temporal dependencies. The integration of an AM enhances the model by weighting and fusing the BiLSTM outputs, thereby refining the prediction accuracy. Through a series of experiments and the application of diverse evaluation metrics, it is demonstrated that the proposed CNN-BiLSTM-AM model surpasses existing models in prediction accuracy and explainability. This advancement positions the model as a significant contribution to the field, offering a robust and insightful tool for highway traffic flow prediction.",
        "output": "Kan et al. (2024) developed an integrated model that combined convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and an attention mechanism, which significantly enhanced highway traffic flow prediction and demonstrated the potential of advanced predictive models in improving traffic safety.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Dong, Y.; Zhang, H.; Wang, C.; Wang, Y. Fine-grained ship classification based on deep residual learning for high-resolution SAR images. Remote Sens. Lett. 2019, 10, 1095\u20131104. \nAbstract: As the resolution of Synthetic Aperture Radar (SAR) images increases, the fine-grained classification of ships has become a focus of the SAR field. In this paper, a ship classification framework based on deep residual network for high-resolution SAR images is proposed. In general, networks with more layers have higher classification accuracy. However, the training accuracy degradation and the limited dataset are major problems in the training process. To build deeper networks, residual modules are constructed and batch normalization is applied to keep the activation function output. Different fine tuning strategies are used to select the best training scheme. To take advantage of the proposed framework, a dataset including 835 ship slices is augmented by different multiples and then used to validate our method and other Convolutional Neural Network (CNN) models. The experimental results show that, the proposed framework can achieve a 99% overall accuracy on the augmented dataset under the optimal fine-tuning strategy, 3% higher than that in other models, which demonstrates the effectiveness of our proposed approach.",
        "output": "Dong et al. (2019) designed a residual learning network for fine-grained ship type recognition in Gaofen-3 SAR imagery, achieving high-accuracy classification of cargo ships, container ships, and oil tankers. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Ju, F.; Wang, Y.; Zhang, Z.; Wang, Y.; Yun, Y.; Guo, H.; Chen, B. A miniature piezoelectric spiral tactile sensor for tissue hardness palpation with catheter robot in minimally invasive surgery. Smart Mater. Struct. 2019, 28, 025033.  \nAbstract: The sense of touch plays a critical role in traditional open surgeries since it could provide tactile feedback to surgeons and is also used to acquire intrinsic properties of tissues through palpation. However, it is partially or completely lost in most existing robot-assisted minimally invasive surgeries. To solve this problem, a miniature tactile sensor with diameter less than 8 mm suitable for catheter robot-based tissue hardness palpation is presented in this paper. The stringent size constraint of minimally invasive surgery (MIS) is met by a unique spiral shape as well as a vertically configured piezoelectric transducer. The spiral shape also helps it achieve a low operating frequency suitable for testing biological tissues. The relationship between electrical impedance of the sensor and mechanical impedance of a load is derived based on the transduction matrix model, which forms the basis of the unique simultaneous actuation and sensing (SAS) technique. As a result, hardness of the load could be sensed from the sensor's electrical impedance by extracting the resonant frequency, with simple instrumentation. The proposed sensor and SAS technique are verified numerically on a finite element model and experimentally on a prototype. After properly choosing the vibration mode and operating frequency range, the sensor is able to perform hardness sensing in a wide range of 0\u20131.7 MPa. In addition, both simulation and experiment results indicate that the sensor has high sensitivity and low variance in the low-hardness region, and relatively lower sensitivity and higher variance in the high-hardness region, suggesting that the sensor can be used in two different sensing modes (quantitative measurement and qualitative classification) in the two regions, respectively. An ex vivo experiment confirms that the sensor could detect the presence, shape and location of an embedded lump from spatial distribution of tissue hardness acquired through grid-based palpation, followed by an improved k-means clustering algorithm. Compared with traditional hardness sensors, this tactile sensor is developed with a unique spiral shape which reduces the operating frequency for enhancing the interaction with biological tissues while keeps the overall size of the sensor as small as possible. And the proposed unique simultaneous actuation and electrical impedance sensing mode helps simplify the instrumentation, making it easier to integrate the sensor into MIS equipment.",
        "output": "Feng Ju et al. (2019) investigated a miniature haptic sensor with a diameter of less than 8 mm suitable for catheterized robotic tissue hardness touching, in order to provide haptic feedback to the surgeon during surgery. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, W.; Yan, B.; Ye, Y.; Yi, W. Direct shear test study on old and new concrete. J. Build. Eng. 2024, 82, 108391. \nAbstract: The interface between new and old concrete is a common feature in prefabricated concrete structures and structural reinforcement. Its shear-slip performance directly impacts the stress performance and deformation capacity of members and structures. This paper aims to examine the influence of roughness density, roughness, roughness treatment, and rebar distribution on the shear performance of the interface by conducting direct shear tests on 14 Z-type specimens without dowel bars and 10 Z-type specimens with dowel bars. The tests reveal that specimens without dowel bars fail in shear brittle, with the roughness density of the interface having the most significant impact on shear strength, followed by roughness, and a minimal effect from the roughness treatment method. In contrast, specimens with dowel bars exhibit shear ductile damage. An increase in the number of inserted bars at a uniform reinforcement ratio leads to increased bond stiffness and shear strength, and a decrease in peak slip. The interface after rough chiseling exhibits the highest shear strength, followed by the interface after broaching, and the interface after grooving has the lowest shear strength. Increasing the roughness or designing dowel bars can enhance the strain coordination ability of the structure, which is beneficial for overall stress loading. Finally, finite element analysis was used to validate the reliability of the tests. Refined modeling of the grooved model without dowel bars revealed that peak height correlates best with shear strength, and that chiseling and other methods of improving the valley depth of the concrete interface at the base level are still superior roughness treatments.",
        "output": "Zhang et al. (2024) found that augmenting the number or distribution density of dowel bars increased the stiffness and shear strength of the joint surface while decreasing the peak displacement. The reliability of their findings was confirmed through analysis using ABAQUS (2021) finite element software.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Nguyen L.N., Nguyen T.D., Dinh T.N., Thai M.T. Optchain: optimal transactions placement for scalable blockchain sharding 2019 IEEE 39th International Conference on Distributed Computing Systems, ICDCS, IEEE (2019), pp. 525-535 \nAbstract: A major challenge in blockchain sharding protocols is that more than 95% transactions are cross-shard. Not only those cross-shard transactions degrade the system throughput but also double the confirmation time, and exhaust an already scarce network bandwidth. Are cross-shard transactions imminent for sharding schemes? In this paper, we propose a new sharding paradigm, called OptChain, in which cross-shard transactions are minimized, resulting in almost twice faster confirmation time and throughput. By treating transactions as a stream of nodes in an online graph, OptChain utilizes a lightweight and on-the-fly transaction placement method to group both related and soon-related transactions into the same shards. At the same time, OptChain maintains a temporal balance among shards to guarantee the high parallelism. Our comprehensive and large-scale simulation using Oversim P2P library confirms a significant boost in performance with up to 10 folds reduction in cross-shard transactions, more than twice reduction in confirmation time, and 50% increase in throughput. When combined with Omniledger sharding protocol, OptChain delivers a 6000 transactions per second throughput with 10.5s confirmation time.",
        "output": "Nguyen et al. (2019) introduced a transaction placement strategy to reduce the cross-shard ratio by placing highly correlated transactions into the same shard. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Grace, N.; Abdei-Sayed, G. Behavior of Externally Draped CFRP Tendons in Prestressed Concrete Bridges. PCI J. 1998, 43, 88\u2013101. \nAbstract: Successful use of carbon fiber reinforced polymer (CFRP) tendons in prestressed concrete bridges can be achieved by combining bonded internal tendons with unbonded externally draped tendons. To examine this theory, four bridge models were tested under static, repeated (7 million cycles), and ultimate loads. Also, the combined effects of factors such as:(a) draping angle;(b) deviator diameter;(c) number of attached die-casts used to anchor the tendons;(d) presence of cushioning material between the deviator and the tendon; and (e) twist angle on the strength of the tendons were examined. It was concluded that the use of externally draped CFRP tendons in bridge construction improves ductility and forces the concrete to undergo inelastic deformation resulting in compression failure. It is also noted that increasing the deviator diameter and using cushioning material at the deviators minimize the reduction in the breaking force of the draped tendon.",
        "output": "In a comprehensive experimental research work, Grace et al. (1998) evaluated the static and fatigue performance of bridges reinforced with bonded internal CFRP tendons and unbonded external CFRP tendons. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Tariq, M.W.; Israr, J.; Farooq, K.; Mujtaba, H. Strength Mechanism of a Swelling Soil Improved with Jute Fibers: A Laboratory Treatment. Geotech. Geol. Eng. 2023, 41, 4367\u20134380. \nAbstract: In this paper, results are reported from a series of laboratory tests conducted on a swelling soil treated with different jute fibers with a twofold objective of reducing their swell characteristics and enhancing their geomechanical properties. The efficacy of passive inclusion of three different jute fibers (i.e., natural, woven, and bitumen coated) in controlling both swell potential and pressure, and improving undrained shear strength and consolidation behavior has been examined. It is observed that the inclusion of jute fibers in the swelling soil expectedly improves both undrained shear strength and CBR value of the treated soil. For instance, the original undrained shear strength improves from 200 kPa to as high as 675 kPa and the original CBR value increases from 3% to a maximum of 7.1%. Similarly, both swell potential and pressure of the treated soil reduced significantly from 4.1% to as low as 1.2% and from 90 kPa to a minimum of 40 kPa, respectively. The improvements in soil properties could be attributed to the reinforcing ability of fibers, which possess a relatively higher tensile strength, in corroboration with the adhesive bond between fibers and soil particles at the micro level. While the former plays an active role in avoiding progression of shear failure, the latter would passively resist the initiation of slip at the soil-fiber interface. Notably, while shear strength of soil generally improves upon addition of jute fibers, inclusion of the bitumen coated fibers has been observed to be more effective than rest.",
        "output": "Wasim M. T. et al. (2023) introduced three different jute fibers to expansive soil and observed increased shear strength and CBR values through mechanical tests. The experimental results further demonstrated the micro-level bonding effect between fiber and soil particles.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Chen, Z.; Wang, D. Numerical analysis of a multi-objective maintenance decision model for sustainable highway networks: Integrating the GDE3 method, LCA and LCCA. Energy Build. 2023, 290, 113096. \nAbstract: A pavement maintenance and rehabilitation decision-making model plays a significant role in the sustainable development of highway networks. However, various maintenance and rehabilitation models lack the capacity to provide multi-objective maintenance decision-making strategies, which are solely concerned with reducing maintenance costs. This study aims to propose a multi-objective maintenance decision-making model, called the Pavement Maintenance-Generalized Differential Evolution 3 (called PM-GDE3), by integrating the pavement condition indices and the generalized differential evolution 3 (GDE3) method. Economic aspect, pavement sustainability, and environmental dimensions were considered in the proposed model to increase the flexibility of pavement management. In this study, the widely-used PAVER maintenance system,which represents a conventional M&R decision-making model and the PM-GDE3 model were applied to estimate the optimal maintenance and rehabilitation schedules for the highway networks, and the results from these models were compared. The results show that the maintenance strategy obtained from the PM-GDE3 model maintains the highway in an acceptable condition. In addition, it has been found that the PM-GDE3 model saves 30.9% of maintenance expenses, about 169 million CNY, 16.9% of carbon emissions, around 4,469 kt, and 11.6% of energy consumption, 2.8GJ, for as long as 30 service years compared to the PAVER model. The PM-GDE3 model outperforms the widely used PAVER maintenance system due to its capacity to propose the optimal solution by establishing a real-time simulation with numerous pavement conditions after maintenance application. This field is the first attempt to combine pavement performance prediction model, life cycle assessment method and life cycle cost assessment. The achievements of the paper are expected to combat the impending energy crisis and climate change impacts of pavement maintenance and rehabilitation.",
        "output": "Chen et al. (2023) combined the generalized differential evolution 3 (GDE3) algorithm, life cycle assessment (LCA), and life cycle cost analysis (LCCA) to construct a multi-objective decision model for highway network maintenance.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Y. Li, X.J. Wang, Y. Wang, Y. Sun, S.Q. Xia, J.F. Zhao\nEffect of biofilm colonization on Pb(II) adsorption onto poly(butylene succinate) microplastic during its biodegradation\nSci. Total Environ., 833 (2022), Article 155251 \nAbstract: Few studies have mentioned the enrichment of heavy metal pollutants on microplastics derived from degradable plastics. This study investigated the adsorption behavior of Pb(II) onto biodegradable poly(butylene succinate) (PBS) microplastics during its biodegradation. The results indicated that Pb(II) adsorbed by biofilm-colonized biodegraded-PBS microplastics (B-PBS) was about 10-folds higher than that of virgin PBS (647.09 \u03bcg\u00b7g\u22121 versus 64.13 \u03bcg\u00b7g\u22121) due to the biofilm colonization and the degradation of PBS. After removing the biofilm, the biodegraded PBS still had high Pb(II) adsorption capacity, which was attributed to the complexation of Pb(II) and the stably adhered extracellular polymeric substances (EPS). Pb(II) adsorption onto both virgin PBS and B-PBS was highly pH-dependent, its adsorption on virgin PBS was dominated by electrostatic interaction, while as for B-PBS, the adsorption mechanisms mainly involved the coordination/complexation of Pb(II) and the EPS components on the colonized biofilm, surface complexation, and electrostatic interaction. This study suggested that the enrichment of heavy metal pollutants onto the biodegradable microplastics may pose risks to the aquatic ecosystem.",
        "output": "Li et al. (2022) noted that Pb adsorbed by biofilm-colonized biodegraded-poly (butylene succinate) microplastics (PBS) was about 10 times higher than that of original PBS. This was because of biofilm colonization and the degradation of PBS. Even after removing biofilm, the biodegraded PBS still had high Pb adsorption capacity. This phenomenon was attributed to the complexation of Pb and the stably adhered extracellular polymeric substances. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Li, Z.; Li, J.; Ding, W.; Cheng, X.; Meng, Z. A sparsity-enhanced periodic OGS model for weak feature extraction of rolling bearing faults. Mech. Syst. Signal Process. 2022, 169, 108733. \nAbstract: The fault symptom of rolling bearings is usually characterized by transient impulses formed at equal intervals, but the impulse signal is easily affected by noise and harmonic interferences, which increases the difficulty of extracting impulse features. In order to realize the effective extraction of weak periodic impulses under strong noise, this paper constructs a non-convex penalty function based on elastic net and Lp norm, and proposes a sparsity-enhanced periodic overlapping group shrinkage (POGS) method to detect rolling bearing faults. In the proposed sparse model, the internal function of the non-convex penalty function adopts the period-guided elastic net group sparse constraint, and the envelope autocorrelation function is used to dynamically update the period prior information to improve the extraction accuracy of highly correlated features within the group. Meanwhile, the non-convex Lp norm is introduced into the penalty function to constrain the sparsity of the overall variables, so as to guide the sparsity within and across groups (SWAG) of faults features while maintaining the weak impulse amplitudes. A comprehensive evaluation indicator is constructed as the fitness function of the moth-flame optimization (MFO) algorithm to realize automatic selection of model parameters. On the basis of the majorization-minimization (MM) algorithm and the improved soft threshold algorithm, the process of solving the objective function of the proposed model is given, and the performance of the proposed method is analyzed. The analysis results of the experimental data of rolling bearings suggest that in comparison with some existing sparse denoising methods, the proposed method exhibits better performance in the extraction of weak periodic impulses.",
        "output": "Li et al. (2022) devised a non-convex penalty function based on an elastic net and the Lp norm, proposing a sparsity-enhanced POGS method for detecting weak periodic impulses.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Chowdhury, M. S. (2023). Comparison of accuracy and reliability of random forest, support vector machine, artificial neural network and maximum likelihood method in land use/cover classification of urban setting. Envir. Chall. 14, 100800. doi:10.1016/j.envc.2023.100800 \nAbstract: Accurate land use and land cover (LULC) is crucial for sustainable urban planning and for many scientific researches. However, the demand for accurate LULC maps is increasing; it is required to compare the classification algorithms to choose the best one. Though, machine and deep learning algorithms are widely used across the world their application is limited in Bangladesh. Accurate urban LULC mapping is challenging because urban heterogeneity affects image classification models in specific feature extraction. In this research, the accuracy of machine learning algorithms (MLA) of RF (Random Forest), SVM (Support Vector Machine), deep learning algorithm (DLA) of ANN (Artificial Neural Network) and traditional Maximum Likelihood (MaxL) method was compared in LULC classification of Dhaka city. Model accuracy of MLA and DLA was tested by statistical indices of sensitivity, specificity, precision, recall F1 etc. There is a high correlation between SVM and ANN models were found. The overall accuracy of the maps was 0.93, 0.94, 0.91 and 0.95 and kappa was 0.89, 0.91, 0.86 and 0.93 for the MaxL, RF, SVM and ANN models respectively. The user accuracy and producer accuracy largely varied according to LULC classes in the applied models. The lowest accuracy of the models was found for bare land classification followed by built-up and vegetation. The high mixture of LULC classes affects the accuracy of built up and bare land classification which produces the lowest accuracy in the MaxL model. The findings indicate that the most accurate and reliable model for urban LULC classification was the ANN model.",
        "output": "Chowdhury (2023), in a comparison of RF, SVM, ANN, and (MaxL), determined that ANN was the most accurate and reliable model for urban LULC classification. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Karim, M.M.; Li, Y.; Qin, R.; Yin, Z. A Dynamic Spatial-Temporal Attention Network for Early Anticipation of Traffic Accidents. IEEE Trans. Intell. Transp. Syst. 2022, 23, 9590\u20139600. \nAbstract: The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated driving vehicles. A computational intelligence model that can accurately and promptly predict accidents from the dashcam video will enhance the preparedness for accident prevention. The spatial-temporal interaction of traffic agents is complex. Visual cues for predicting a future accident are embedded deeply in dashcam video data. Therefore, the early anticipation of traffic accidents remains a challenge. Inspired by the attention behavior of humans in visually perceiving accident risks, this paper proposes a Dynamic Spatial-Temporal Attention (DSTA) network for the early accident anticipation from dashcam videos. The DSTA-network learns to select discriminative temporal segments of a video sequence with a Dynamic Temporal Attention (DTA) module. It also learns to focus on the informative spatial regions of frames with a Dynamic Spatial Attention (DSA) module. A Gated Recurrent Unit (GRU) is trained jointly with the attention modules to predict the probability of a future accident. The evaluation of the DSTA-network on two benchmark datasets confirms that it has exceeded the state-of-the-art performance. A thorough ablation study that assesses the DSTA-network at the component level reveals how the network achieves such performance. Furthermore, this paper proposes a method to fuse the prediction scores from two complementary models and verifies its effectiveness in further boosting the performance of early accident anticipation.",
        "output": "Muhammad et al. (2022) proposed a dynamic spatial-temporal attention (DSTA) network that utilized dashcam video data to predict traffic accidents early by learning the spatial-temporal features, enhancing accident prevention preparedness.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, J.; Wen, N.; Sun, Q.; Horton, R.; Liu, G. The effect of macropore morphology of actual anecic earthworm burrows on water infiltration: A COMSOL simulation. J. Hydrol. 2023, 618, 129261. \nAbstract: Soil macropores impact water infiltration. Due to the complexity of macropore structure, most macropore soil water dynamic simulations use simplified assumptions, such as cylindrical shape macropores, which do not well represent fluid flow in actual macropores. In this study, 3D digitalized structures of actual anecic earthworm burrows are obtained by combining tin casting with a 3D scanner. The in-situ earthworm burrows are imported into finite element numerical simulation software (COMSOL). Based on simulations, the effects of burrow spatial characteristics, such as number (N), length (L), average diameter (Davg), and tortuosity (\u03c4) of partially penetrating (non-through) and fully penetrating (through) burrows, on water infiltration are clarified. The N value of non-through burrows correlates significantly with preferential flow infiltration rates (r = 1). In addition to the N value, the L value of non-through burrows is an important factor affecting preferential flow infiltration (r = 0.99). For the through earthworm burrows, macroporosity (\u03b5p) is the best predictor of Ksat. Unlike Davg and L, the \u03c4 of burrows has a low correlation coefficient with Ksat. The increase of adjacent infiltration is N-dependent for non-through burrows and is N-independent for through burrows. These findings demonstrate that actual macropore morphology can be used for numerical simulations, which provides a new pathway forward for pore-scale soil water dynamic research.",
        "output": "Zhang et al. (2023) pointed out that soil macropores, as preferential flow pathways, could rapidly transport water, air, and chemicals through the soil when they simulated the effect of macropore morphology on water infiltration by using COMSOL.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Liu, X.; Yu, W.; Huang, Y.; Yang, G.; You, W.; Gao, L. Long-Term Behaviour of Recycled Aggregate Concrete Beams Prestressed with Carbon Fibre-Reinforced Polymer (CFRP) Tendons. Case Stud. Constr. Mater. 2023, 18, e01785. \nAbstract: The utilisation of recycled aggregate concrete (RAC) is commonly recognised as one of the most effective means to achieve cleaner and sustainable development in civil engineering. To promote the application of RAC, prestressing technique can be employed to overcome the inherent disadvantages of RAC beams associated with poor cracking resistance and large deflections. However, the research on the prestressed RAC beam is quite limited, and no research has been performed on their long-term behaviour. This paper presents a finite element (FE) analysis for investigating the long-term behaviour of RAC beams prestressed with carbon fibre-reinforced polymer (CFRP) tendons considering the effects of concrete creep, concrete shrinkage, tendon relaxation as well as the cracking and tension stiffening of concrete. Based on the principle of superposition, the variations of the stress and strain with time are considered in the numerical analysis using step-by-step method. The FE model is calibrated with the experimental results obtained from the literature. Based on the validated model, a comprehensive parametric study is performed to investigate the effects of the replacement ratio of recycled coarse aggregate (RCA), concrete strength, reinforcement ratio, prestress level, and sustained load level on the long-term behaviour of prestressed RAC beams. The obtained results demonstrate that increasing the prestress load is an effective way to reduce the long-term deflection of RAC beams, and the use of RAC with low RCA replacement ratio is suggested. Besides, the main causes of the long-term deflection and axial shorting of the CFRP prestressed RAC beams are also studied. This research provides a pioneering and insightful study of the long-term behaviour of CFRP prestressed RAC beams. The obtained results demonstrate that the time-dependent effects should be well considered in the design before the prestressed RAC beam is used in practice.",
        "output": "Liu et al. (2023) explored the long-term performance of concrete beams reinforced with CFRP tendons via FE analysis, factoring in concrete creep, shrinkage and tendon relaxation. The model accuracy was confirmed by experimental outcomes, with an error of no more than 5%.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Xiong, Y.; Zhang, J.; Xu, X.; Yan, Y.; Sun, S.; Liu, S. Strategies for improving the microclimate and thermal comfort of a classical Chinese garden in the hot-summer and cold-winter zone. Energy Build. 2020, 215, 109914. \nAbstract: The current study reports on strategies for improving the microclimate and thermal comfort modification effect of urban green spaces in the hot-summer and cold-winter zone. A classical Chinese garden (Lingering Garden) located south of the Yangtze River, China was selected as the study area. The microclimate parameters of the garden, including air temperature, relative humidity, and wind speed, as well as the standard effective temperature (SET*) were obtained using field-measurement-validated ENVI-met model simulations. The water bodies, trees, and buildings in the garden were redesigned by varying their coverage or density. The microclimate parameters and SET* values of the redesigned scenarios were then compared with those of the actual garden. The results indicated that the garden generally exhibited a modification effect. A number of available design strategies were proposed. The microclimate and thermal comfort of a classical Chinese garden can generally be improved by increasing the water coverage and decreasing the building coverage, as well as optimizing the tree coverage. The SET* value can be decreased by more than 1\u202f\u00b0C on hot summer days if the water body coverage is increased from 10% to 40%; the SET* value can be reduced by approximately 0.5\u202f\u00b0C if the tree coverage is increased from 35% to 70%, while the SET* value is approximately 0.25\u202f\u00b0C lower for 15% tree coverage than it is for of 35% tree coverage. In addition, the difference of SET* values between the cases of 10% and 30% building coverage can reach as much as 1\u202f\u00b0C. Therefore, various landscape elements should be comprehensively considered in order to achieve more comfortable thermal conditions.",
        "output": "Xiong et al. (2020) redesigned the coverage and density of water bodies, trees, and buildings in the Lingering Garden to improve its microclimate and thermal comfort.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Burbey, T. J., and Zhang, M. (2015). Inverse modeling using PS-InSAR for improved calibration of hydraulic parameters and prediction of future subsidence for Las Vegas Valley, USA. Proc. Int. Assoc. Hydrological Sci. 372 (372), 411\u2013416. doi:10.5194/piahs-372-411-2015 \nAbstract: Las Vegas Valley has had a long history of surface deformation due to groundwater pumping that began in the early 20th century. After nearly 80 years of pumping, PS-InSAR interferograms have revealed detailed and complex spatial patterns of subsidence in the Las Vegas Valley area that do not coincide with major pumping regions. High spatial and temporal resolution subsidence observations from InSAR and hydraulic head data were used to inversely calibrate transmissivities (), elastic and inelastic skeletal storage coefficients ( and ) of the developed-zone aquifer and conductance (CR) of the basin-fill faults for the entire Las Vegas basin. The results indicate that the subsidence observations from PS-InSAR are extremely beneficial for accurately quantifying hydraulic parameters, and the model calibration results are far more accurate than when using only water-levels as observations, and just a few random subsidence observations. Future predictions of land subsidence to year 2030 were made on the basis of existing pumping patterns and rates. Simulation results suggests that subsidence will continue in northwest subsidence bowl area, which is expected to undergo an additional 11.3\u202f of subsidence. Even mitigation measures that include artificial recharge and reduced pumping do not significantly reduce the compaction in the northwest subsidence bowl. This is due to the slow draining of thick confining units in the region. However, a small amount of uplift of 0.4\u202f is expected in the North and Central bowl areas over the next 20 years.",
        "output": "Burbey and Zhang (2015) used high spatial and temporal resolution subsidence observation of InSAR and hydraulic head data to inversely calibrate the hydrogeological parameters of the development zone aquifer in the entire Las Vegas Basin. They found that the subsidence observation using PS-InSAR is extremely beneficial to accurately quantify the hydraulic parameters, and the model calibration results are far more accurate than only using the water level as the observation value and a small number of random subsidence observations.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Pearlmutter, D.; Berliner, P.; Shaviv, E. Evaluation of Urban Surface Energy Fluxes Using an Open-Air Scale Model. J. Appl. Meteorol. Climatol. 2005, 44, 532\u2013545. \nAbstract: The thermal behavior of an urban surface is crucial to understand, but it is difficult to predict using conventional measurement or modeling approaches. In this study, an integrated method is proposed for evaluating urban energy exchanges with an open-air scale model of a building-street canyon surface array. The technique, which potentially combines the flexibility of modeling with the reliability of empirical observation under natural turbulence and radiative loading, is tested in hot, arid summer conditions to gauge its ability for reproducing surface-atmosphere energy fluxes that are representative of diurnal patterns in actual urban settings. After identifying the inertial sublayer, which is created above the scaled roughness array at a point near its downwind edge, roughness parameters utilized in the calculation of turbulent sensible heat flux are determined for two different array configurations of varying frontal area density and compared with existing data from field studies and morphometric models. For each geometric configuration, the relative sharing of radiant energy between storage and turbulent fluxes is compared with published findings obtained by conventional methods, as is the diurnal pattern of each component flux. Roughness parameters that are obtained conform to the expected ranges, as do daytime and overall daily fluxes and flux ratios. Overall, radiation absorption and heat storage are higher in the array with deeper canyons, and in both arrays the share of sensible heat channeled into the atmosphere is both higher in magnitude and later in reaching its peak intensity than that which is stored within the scaled urban fabric. This thermal time lag, when evaluated by fitting data to a published model for parameterizing heat storage from net radiation, shows a high correlation with hysteresis behavior in actual cities.",
        "output": "Pearlmutter et al. (2005) introduced an integrated method combining open-air scale models with empirical observations to evaluate urban surface thermal exchanges. This approach benefits from the flexibility of modeling and the reliability of field observations, effectively simulating and predicting thermal exchanges and energy flows in urban microclimates.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Nguyen, L.; Fatahi, B. Behaviour of clay treated with cement & fibre while capturing cementation degradation and fibre failure\u2014C3F Model. Int. J. Plast. 2016, 81, 168\u2013195. \nAbstract: Soil treated with cement becomes brittle because its shear strength decreases rapidly in a post-peak state, which is why in recent years the inclusion of fibre into soil treated with cement has become an increasingly popular research area. This paper presents a constitutive model to simulate the behaviour of the fibre reinforced cement treated soil, referred to as the improved soil composite. In this model, a non-linear failure envelope was formulated to merge with the Critical State Line (CSL) of the reconstituted soil mixture at high levels of stress in order to capture the broken cementation bonds and ruptured fibre. A non-associated plastic potential function and a general stress strain relationship that includes the softening of the composite soil were also proposed to simulate the pre-and-post peak state.\nMoreover, many researchers focus on the addition of fibre into sand, soft clay, and sand treated with cement, whereas the behaviour of soft clay treated with fibre and cement requires further investigation. Hence, in this study a series of undrained triaxial tests were carried out on natural Ballina clay treated with cement and 0.3%\u20130.5% of fibre to determine how the amount of fibre and cement affects the behaviour of soft clay. SEM images were also analysed to study the structure of the improved Ballina composite at the micro-structural level. The laboratory results indicated that the combined effects of cementation and fibre reinforcement increased the shear strength and ductility of treated soft clay. Under triaxial conditions the peak shear strength of soft clay treated with cement and fibre increases dramatically due to the formation of cementation bonds and the bridging effect provided by the fibres, and the brittleness caused by the cementation bonds breaking also improves significantly due to the inclusion of fibre. However, when shearing at a high mean effective stress the cementation bonds break and the fibre ruptures due to the mean effective stresses and plastic deviatoric strain which caused major cracks to appear within the sample.\nThe performance of the model was evaluated by comparing its predictions with the results of the undrained triaxial tests conducted on the improved Ballina clay composite. By capturing the main features of the composite soil the model provided reliable predictions that agreed with the experimental results.",
        "output": "Nguyen L. et al. (2016) conducted a series of undrained triaxial tests on natural Ballina clay treated with cement and 0.3% to 0.5% fibers. The results showed that the peak shear strength of the cement- and fiber-treated soft clay increased significantly due to the formation of cement bonds and the bridging effect provided by the fibers.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Luu, L., Narayanan, V., Zheng, C., Baweja, K., Gilbert, S., Saxena, P., 2016. A secure sharding protocol for open blockchains. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. pp. 17\u201330. \nAbstract: Cryptocurrencies, such as Bitcoin and 250 similar alt-coins, embody at their core a blockchain protocol --- a mechanism for a distributed network of computational nodes to periodically agree on a set of new transactions. Designing a secure blockchain protocol relies on an open challenge in security, that of designing a highly-scalable agreement protocol open to manipulation by byzantine or arbitrarily malicious nodes. Bitcoin's blockchain agreement protocol exhibits security, but does not scale: it processes 3--7 transactions per second at present, irrespective of the available computation capacity at hand.\nIn this paper, we propose a new distributed agreement protocol for permission-less blockchains called ELASTICO. ELASTICO scales transaction rates almost linearly with available computation for mining: the more the computation power in the network, the higher the number of transaction blocks selected per unit time. ELASTICO is efficient in its network messages and tolerates byzantine adversaries of up to one-fourth of the total computational power. Technically, ELASTICO uniformly partitions or parallelizes the mining network (securely) into smaller committees, each of which processes a disjoint set of transactions (or \"shards\"). While sharding is common in non-byzantine settings, ELASTICO is the first candidate for a secure sharding protocol with presence of byzantine adversaries. Our scalability experiments on Amazon EC2 with up to $1, 600$ nodes confirm ELASTICO's theoretical scaling properties.",
        "output": "Luu et al. (2016) pioneered the first blockchain sharding protocol, Elastico, which realizes the linear growth of blockchain throughput with the number of shards by assigning transactions to multiple independent sharding networks for processing. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Wang, H., Xu, W., Shao, J., and Skoczylas, F. (2014). The gas permeability properties of low-permeability rock in the process of triaxial compression test. Mater. Lett. 116, 386\u2013388. doi:10.1016/j.matlet.2013.11.061 \nAbstract: Natural low-permeability rock of granitic gneiss is excellent material for underground oil depot. Its microstructure and mineral composition are analyzed by SEM-EDS, the triaxial tests under different confining pressures are carried out. The evolution law of gas permeability with stress in the process of deformation and failure is discussed. The permeability property of granitic gneiss is different from that of the rock with large porosity, the curve of permeability with stress in the process of deformation and failure is relatively flat and no large fluctuations, but still reflects the compression, weakening and failure characteristics of rock samples, and the effect of confining pressure on the permeability is not very obvious due to its dense structure and small porosity.",
        "output": "Wang et al. (Wang et al., 2014) used a particle flow code (PFC) fluid-solid coupling model to simulate the hydraulic fracture extension process, thereby verifying the reasonableness of the PFC fluid\u2013solid coupling model. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Ng, C.; Zareinia, K.; Sun, Q.; Kuchenbecker, K.J. Stiffness perception during pinching and dissection with teleoperated haptic forceps. In Proceedings of the 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Lisbon, Portugal, 28\u201331 August 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 456\u2013463. \nAbstract: Robotic-assisted surgery requires an intuitive and effective human-machine interface. Providing haptic feedback for pinching and dissecting motions of bipolar forceps, a tool commonly used in neurosurgery, could potentially improve the surgeon's experience. Current haptic hand controllers have limited actuation and feedback capability, requiring surgeons to hold the handle differently compared to a conventional tool. This paper presents a new master design that provides 1-DOF force feedback by adding a Hall-effect sensor and a voice coil actuator directly onto a bipolar forceps. Twenty participants used this interface to perform a remote stiffness perception test that employed the method of constant stimuli. Ten participants pinched the samples, and the other ten dissected them. Each participant did two blocks of 35 trials with only visual feedback or with visual and haptic feedback in random order. Psychometric functions were created from the results to compare perceptual capabilities, metrics were calculated from the force and position data, and participant survey responses were analyzed. The results show that providing the force feedback made the task seem easier, increased the participant's confidence, and reduced the total tip distance traveled in the pinching task. The haptic feedback slightly improved stiffness perception in the pinching task but did not improve perception in the dissection task. These results support the utility of a force-feedback attachment to conventional forceps for pinching and motivate further investigation into the design for dissection.",
        "output": "Canaan Ng et al. (2017) provided a one-DOF force feedback device for surgical tweezers by adding a Hall effect sensor directly to the surgical tweezers and a voice coil actuator to provide one-DOF force feedback. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "He, Y.; Jian, T.; Su, F.; Qu, C.; Gu, X. Novel Range-Spread Target Detectors in Non-Gaussian Clutter. IEEE Trans. Aerosp. Electron. Syst. 2010, 46, 1312\u20131328. \nAbstract: Range-spread target detection in spherically invariant random vector clutter is addressed, and different detectors with constant false alarm rate (CFAR) property are devised by exploiting order statistics theory. Firstly, with a known normalized clutter covariance matrix, the generalized likelihood ratio test based on order statistics (OS-GLRT) utilizes some largest observations from the range cells occupied by the most likely target scatterers. OS-GLRT is robust when the estimated number of scatterers is somewhat larger than the actual, but is degraded for smaller estimations. To improve the robustness of OS-GLRT, an OS-GLRT with dynamic threshold (DOS-GLRT) is designed, which adjusts detection threshold dynamically. By replacing the ideal normalized clutter covariance matrix with the constrained approximate maximum likelihood (ML) estimated matrix based on secondary data only, the adaptive OS-GLRT and adaptive DOS-GLRT are also obtained. The performance assessment conducted by Monte Carlo simulation confirms the effectiveness of the proposed detectors.",
        "output": "He et al. (2010) proposed order statistics GLRT (OS-GLRT), which essentially assumes that the number of scatterers and secondary data is known. SDD-GLRT and OS-GLRT use prior knowledge of the spatial scatterer density, which is unattainable for targets in space surveillance that are always non-cooperative. Therefore, the detection performance will decrease when there is a mismatch in prior information. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Q.J. Wang, Y. Zhang, X.X. Wangjin, Y.L. Wang, G.H. Meng, Y.H. Chen The adsorption behavior of metals in aqueous solution by microplastics effected by UV radiation J. Environ. Sci., 87 (2020), pp. 272-280 \nAbstract: Microplastics are considered as the carrier to heavy metals in the environment. But the sorption ability of microplastics influenced by photo-aging is remaining unclear. In the present study, the sorption of two kinds of metal ions (Cu2+ and Zn2+) in the aqueous solution by both the virgin and aged microplastics was investigated. Polyethylene terephthalate (PET) debris, one of the typical kinds of microplastics was chosen in this study. Photo-aging of microplastics in environment was simulated using UV radiation in the laboratory. Date analysis indicated that the aged microplastics had higher adsorption capacity of heavy metals than original ones. This could be related to the increased surface area and oxygen containing function appeared in the surface of aged microplastics after UV radiation. When prolonging the time of radiation, the enhanced adsorption capacities of microplastics appeared for Cu2+ and Zn2+. These results showed a great interaction between the aging degree of plastics and sorption capacity to heavy metals. Meanwhile, external conditions including temperature and pH value were also showed great influence to the adsorption behavior.",
        "output": "Wang et al. (2020) noted that photodegraded polyethylene terephthalate (PET) had higher adsorption capacity of heavy metals than original PET. They attributed this to increased surface area and oxygen containing functions due to UV light radiation.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Tang, G.; Zhao, H.; Claramunt, C.; Zhu, W.; Wang, S.; Wang, Y.; Ding, Y. PPA-Net: Pyramid Pooling Attention Network for Multi-Scale Ship Detection in SAR Images. Remote Sens. 2023, 15, 2855. \nAbstract: In light of recent advances in deep learning and Synthetic Aperture Radar (SAR) technology, there has been a growing adoption of ship detection models that are based on deep learning methodologies. However, the efficiency of SAR ship detection models is significantly impacted by complex backgrounds, noise, and multi-scale ships (the number of pixels occupied by ships in SAR images varies significantly). To address the aforementioned issues, this research proposes a Pyramid Pooling Attention Network (PPA-Net) for SAR multi-scale ship detection. Firstly, a Pyramid Pooled Attention Module (PPAM) is designed to alleviate the influence of background noise on ship detection while its parallel component favors the processing of multiple ship sizes. Different from the previous attention module, the PPAM module can better suppress the background noise in SAR images because it considers the saliency of ships in SAR images. Secondly, an Adaptive Feature Balancing Module (AFBM) is developed, which can automatically balance the conflict between ship semantic information and location information. Finally, the detection capabilities of the ship detection model for multi-scale ships are further improved by introducing the Atrous Spatial Pyramid Pooling (ASPP) module. This innovative module enhances the detection model\u2019s ability to detect ships of varying scales by extracting features from multiple scales using atrous convolutions and spatial pyramid pooling. PPA-Net achieved detection accuracies of 95.19% and 89.27% on the High-Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD), respectively. The experimental results demonstrate that PPA-Net outperforms other ship detection models.",
        "output": "Tang et al. (2023), designed a Pyramid Mixed Attention Module (PPAM) to mitigate the effect of background noise on ship detection, while its parallel component facilitates the processing of multiple ship sizes.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Oh, J.-S.; Han, Y.-M.; Lee, S.-R.; Choi, S.-B. A 4-DOF haptic master using ER fluid for minimally invasive surgery system application. Smart Mater. Struct. 2013, 22, 045004.  \nAbstract: This paper presents a novel 4-degrees-of-freedom (4-DOF) haptic master using a electrorheological (ER) fluid which is applicable to minimally invasive surgery (MIS) systems. By adopting a controllable ER fluid, the master can easily generate 4-DOF repulsive forces with the advantages of a simple mechanism and continuous force control capability. The proposed master consists of two actuators: an ER spherical joint for 3-DOF rotational motion and an ER piston device for 1-DOF translational motion. The generated torque/force models are mathematically derived by analyzing the mechanism geometry and using the Bingham characteristics of an ER Fluid. The haptic master is optimally designed and manufactured based on the mathematical torque/force models. The repulsive torque/force responses are experimentally evaluated and expressed by the first-order and second-order dynamic equations for each motion. A sliding mode controller (SMC), which is known to be robust to uncertainties, is then designed and empirically implemented to achieve the desired torque/force trajectories. It is demonstrated by presenting torque/force tracking results of both rotational and translational motions that the proposed 4-DOF ER haptic master integrated with the SMC can provide an effective haptic control performance for MIS applications.",
        "output": "Jong-Seok Oh et al. (2013) proposed a novel four-DOF haptic master hand; by employing a controllable current-variable fluid, the master hand generated a four-DOF repulsive force, which had the advantages of a simple mechanism and the ability to control continuous force.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Payne, C.J.; Rafii-Tari, H.; Marcus, H.J.; Yang, G.Z. Hand-held microsurgical forceps with force-feedback for micromanipulation. In Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, 31 May\u20137 June 2014; IEEE: Piscataway, NJ, USA, 2014; pp. 284\u2013289. \nAbstract: This paper presents a hand-held microsurgical forceps design with force-feedback capabilities designed for micromanipulation tasks. The device uses a customized force sensor that measures grasping forces over a range of 0-300mN and uses an actuator to exert amplified forces back on to the operator's fingertip in a mechanically-ungrounded setup. This allows perception of low force levels that are otherwise imperceptible to human touch. A customized force sensor design for the forceps grasping measurement is presented and a calibration experiment was conducted to validate its linearity and repeatability. A bench test of the device was conducted to demonstrate its intrinsic force-amplifying capabilities, with amplification factors of up to \u00d750 reported. A user study was conducted to confirm that the device could significantly improve human perception of grasping forces compared to conventional microsurgical forceps with the results demonstrating an order-of-magnitude improvement in force perception.",
        "output": "Christopher J. Payne et al. (2014) proposed a novel microsurgical forceps with amplified force feedback and used an actuator to apply a mechanically ungrounded device to the operator\u2019s fingertip by an amplified force. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Clayton, L. K., Schaefer, K., Battaglia, M. J., Bourgeau-Chavez, L., Chen, J., Chen, R. H., et al. (2021). Active layer thickness as a function of soil water content. Environmental Research Letters, 16(5), 055028. https://doi.org/10.1088/1748-9326/abfa4c \nAbstract: Active layer thickness (ALT) is a critical metric for monitoring permafrost. How soil moisture influences ALT depends on two competing hypotheses: (a) increased soil moisture increases the latent heat of fusion for thaw, resulting in shallower active layers, and (b) increased soil moisture increases soil thermal conductivity, resulting in deeper active layers. To investigate their relative influence on thaw depth, we analyzed the Field Measurements of Soil Moisture and Active Layer Thickness (SMALT) in Alaska and Canada dataset, consisting of thousands of measurements of thaw depth and soil moisture collected at dozens of sites across Alaska and Canada as part of NASA's Arctic Boreal Vulnerability Experiment (ABoVE). As bulk volumetric water content (VWC) integrated over the entire active layer increases, ALT decreases, supporting the latent heat hypothesis. However, as VWC in the top 12 cm of soil increases, ALT increases, supporting the thermal conductivity hypothesis. Regional temperature variations determine the baseline thaw depth while precipitation may influence the sensitivity of ALT to changes in VWC. Soil latent heat dominates over thermal conductivity in determining ALT, and the effect of bulk VWC on ALT appears consistent across sites.",
        "output": "The amount and distribution of water content in the active layer are key factors for determining the ALT, which further regulates the permafrost responses to climate patterns and extremes (Clayton et al., 2021). ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "N.N. Wu, W.R. Xiang, F. Zhu, Z.L. Huo, Z.Y. Wang Oxidative degradation and possible interactions of coexisting decabromodiphenyl ether (BDE-209) on polystyrene microplastics in UV/chlorine process Water Res., 245 (2023), Article 120560 \nAbstract: This work was to investigate the transformation of coexisting decabromodiphenyl ether (BDE-209) on microplastics and their possible interactions in UV/chlorine process. Compared with pristine microplastics, the highly aged polystyrene (PS) showed an inhibitory effect on degradation of BDE-209. Increasing initial concentration of BDE-209 on PS inhibited degradation, while the chlorine concentration and pH did not affect the final degradation efficiency. Moreover, the presence of NO3\u2212, SO42\u2212, HCO3\u2212 and HA in water was unfavorable for BDE-209 degradation. According to the experimental and calculation results, the contribution to the degradation of BDE-209 was ranked as direct photolysis > HO\u2022 > \u2022Cl in the UV/ chlorine system. Chlorination products released by PS during UV/chlorination were detected. Four possible reaction pathways of BDE-209 were proposed, which mainly involved debromination, hydroxylation, chlorine substitution, cleavage of ether bond, and intramolecular elimination of HBr. It was worth noting that PS microplastics not only inhibited the degradation of BDE-209, but also affected the type and abundance of its transformation products. Meanwhile, interaction products of PS and BDE-209 were determined, which was attributed to reactions of PS-derived radicals with \u2022Br/\u2022C6Br5 and \u2022Cl. Results of toxicity evaluation showed that the introduction of carbon-halogen bonds, especially C-Br bond, increased the toxicity of chain scission products of PS. This work provides some new insights into transformation, interaction, and associated ecological risks of coexisting microplastics and surface adsorbed contaminants in the UV/chlorine process of drinking water treatment plants (DWTPs) and wastewater treatment plants (WWTPs).",
        "output": "Wu et al. (2023) found that photodegraded polystyrene (PS) inhibited the degradation of decabromodiphenyl ether (one of typical additives in plastic products as fire retardants). UV light radiation also introduced carbon-halogen bonds, especially C\u2013Br bond and increased the toxicity of chain scission products of PS.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Tang, X.; Sun, Y.; Liu, S.; Yang, Y. DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 17\u201324 June 2023; pp. 11422\u201311432. \nAbstract: This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due to an insight: the encoder and the decoder in DETR are both based on the attention mechanism and are thus capable of aggregating semantics across the entire image. The aggregation results, ie, image-level predictions, can naturally exploit the weak supervision for domain alignment. Such motivated, we propose DETR with additional Global Aggregation (DETR-GA), a CDWSOD detector that simultaneously makes\" instance-level+ image-level\" predictions and utilizes\" strong+ weak\" supervisions. The key point of DETR-GA is very simple: for the encoder/decoder, we respectively add multiple class queries/a foreground query to aggregate the semantics into image-level predictions. Our query-based aggregation has two advantages. First, in the encoder, the weakly-supervised class queries are capable of roughly locating the corresponding positions and excluding the distraction from non-relevant regions. Second, through our design, the object queries and the foreground query in the decoder share consensus on the class semantics, therefore making the strong and weak supervision mutually benefit each other for domain alignment. Extensive experiments on four popular cross-domain benchmarks show that DETR-GA significantly improves CSWSOD and advances the states of the art (eg, 29.0%--> 79.4% mAP on PASCAL VOC--> Clipart_all dataset).",
        "output": "Tang et al. (2023), proposed a cross-domain weakly supervised approach based on the DETR cross-domain weakly supervised target detection (CDWSOD) method. The aim is to adapt the detector from the source domain to the target domain through weak supervision.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Chen, P.; Xu, S.; Zhou, X.; Xu, D. An Experimental Study on Flexural-Shear Behavior of Composite Beams in Precast Frame Structures with Post-Cast Epoxy Resin Concrete. Buildings 2023, 13, 3137. \nAbstract: Epoxy resin concrete has superior mechanical properties compared to ordinary concrete, and will play an increasingly important role in urban construction. In this paper, the application effect and prospect of epoxy resin concrete in precast composite frame structures are discussed. Taking the joint surface of the old and new concrete at the end of the composite beam as the research object, three specimens were devised and fabricated. Subsequently, a horizontal cyclic load test was conducted, and the seismic performance indices were analyzed. Multiple finite element models were established to assess the influence of precast concrete strength, the diameter of the longitudinal bar of the beam, the shear span ratio, and the epoxy resin concrete post-cast area, among other factors, on the seismic performance of the beam end. Four findings indicate the following: Firstly, epoxy resin concrete, characterized by its high performance attributes, can be used as a post-cast material in precast concrete structures. Secondly, when the strength of the post-cast epoxy concrete approximates or slightly exceeds that of the precast concrete, and the ratio of longitudinal reinforcement and shear span ratio are appropriately balanced, the operational performance of the composite beam frame structure is enhanced. In addition, when post-cast epoxy resin concrete is employed in the beam-column joint area, the mechanical performance of the composite beam end in the joint area matches or even surpasses that of the structure that was cast in situ. And subsequently, the expansion of post-cast area resulted in better mechanical performance. Finally, when the area of post-cast epoxy resin concrete is a non-node area, the mechanical properties of the composite beam end are worse than the former. However, the amount of epoxy resin concrete used will be greatly reduced, and as the precast node area expands, the bearing capacity of the beam end will increase and gradually approach the cast-in situ structure, indicating that this construction scheme also has advantages.",
        "output": "Chen et al. (2023) performed experiments and numerical simulations on monolithically cast frame beam\u2013column joints and composite frame structures with post-cast ordinary and epoxy resin cement. Their findings indicate that the mechanical characteristics of beam\u2013column joints with post-cast ordinary concrete were lesser than those of cast-in situ joints, while those reinforced with post-cast epoxy resin concrete matched or surpassed the in situ counterparts.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhou, G.; Zhang, G.; Xue, B. A maximum-information-minimum-redundancy-based feature fusion framework for ship classification in moderate-resolution SAR image. Sensors 2021, 21, 519.  \nAbstract: High-resolution synthetic aperture radar (SAR) images are mostly used in the current field of ship classification, but in practical applications, moderate-resolution SAR images that can offer wider swath are more suitable for maritime surveillance. The ship targets in moderate-resolution SAR images occupy only a few pixels, and some of them show the shape of bright spots, which brings great difficulty for ship classification. To fully explore the deep-level feature representations of moderate-resolution SAR images and avoid the \u201cdimension disaster\u201d, we innovatively proposed a feature fusion framework based on the classification ability of individual features and the efficiency of overall information representation, called maximum-information-minimum-redundancy (MIMR). First, we applied the Filter method and Kernel Principal Component Analysis (KPCA) method to form two feature subsets representing the best classification ability and the highest information representation efficiency in linear space and nonlinear space. Second, the MIMR feature fusion method is adopted to assign different weights to feature vectors with different physical properties and discriminability. Comprehensive experiments on the open dataset OpenSARShip show that compared with traditional and emerging deep learning methods, the proposed method can effectively fuse non-redundant complementary feature subsets to improve the performance of ship classification in moderate-resolution SAR images.",
        "output": "Zhou et al. (2021) introduced MIMR, an optimization framework designed to maximize information content while minimizing redundancy. This framework allows for the extraction of a non-redundant subset of complementary features, enhancing feature representativeness and ultimately improving the classification performance of ships with limited pixel information in medium-resolution SAR images.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Mahmoudpour, M., Khamehchiyan, M., Nikudel, M. R., and Ghassemi, M. R. (2016). Numerical simulation and prediction of regional land subsidence caused by groundwater exploitation in the southwest plain of Tehran, Iran. Iran. Eng. Geol. 201, 6\u201328. doi:10.1016/j.enggeo.2015.12.004 \nAbstract: This study characterizes land subsidence in southwest plain of Tehran using numerical modeling and predicts the trend through 2018. Excessive groundwater withdrawal has caused severe land subsidence in Tehran; in the past 28 years (1984\u20132012), groundwater level has decreased 11.65 m. The multi-layered aquifer system in the southwestern plain of Tehran contains three aquifers and three aquitard units. The present model was developed simulation using PMWIN (MODFLOW for Windows). First, groundwater level and land subsidence were simulated for the end of 2004. The model was calibrated using hydraulic head measurements and InSAR data. The simulation results were in fairly good agreement with the measurement results. The calibrated and evaluated model was then used to assess the future evolution of land subsidence and for prediction of subsidence through the end of 2018. Numerical results show that, assuming a constant rate of pumping in the future, land subsidence in the southwestern plain of Tehran will reach 33 cm by 2018. The study confirmed that land subsidence caused by groundwater pumping is a serious threat to southwest Tehran.",
        "output": "Masoud Mahmoudpour et al. (2016) used head and InSAR data for model calibration and verified that the prediction results suitably agreed with the measurement results. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Gerlach, K. Spatially distributed target detection in non-Gaussian clutter. IEEE Trans. Aerosp. Electron. Syst. 1999, 35, 926\u2013934. \nAbstract: Two detection schemes for the detection of a spatially distributed, Doppler-shifted target in non-Gaussian clutter are developed. The non-Gaussian clutter is modeled as a spherically invariant random vector (SIRV) distribution. For the first detector, called the non-scatterer density dependent generalized likelihood ratio test (NSDD-GLRT), the detector takes the form of a sum of logarithms of identical functions of data from each individual range cell. It is shown under the clutter only hypothesis, that the detection statistic has the chi-square distribution so that the detector threshold is easily calculated for a given probability of false alarm P/sub F/. The detection probability P/sub D/ is shown to be only a function of the signal-to-clutter power ratio (S/C)/sub opt/ of the matched filter, the number of pulses N, the number of target range resolution cells J, the spikiness of the clutter determined by a parameter of an assumed underlying mixing distribution, and P/sub F/. For representative examples, it is shown that as N, J, or the clutter spikiness increases, detection performance improves. A second detector is developed which incorporates a priori knowledge of the spatial scatterer density. This detector is called the scatterer density dependent GLRT (SDD-GLRT) and is shown for a representative case to improve significantly the detection performance of a sparsely distributed target relative to the performance of the NSDD-GLRT and to be robust for a moderate mismatch of the expected number of scatterers. For both the NSDD-GLRT and SDD-GLRT, the detectors have the constant false-alarm rate (CFAR) property that P/sub F/ is independent of the underlying mixing distribution of the clutter, the clutter covariance matrix, and the steering vector of the desired signal.",
        "output": "Gaussian clutter scene, Gerlach (1999) proposed a scatterer density-dependent generalized likelihood ratio test (SDD-GLRT) using prior knowledge of the spatial scatterer density and the clutter covariance matrix.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Galdames, F.J.; Perez, C.A.; Est\u00e9vez, P.A.; Adams, M. Rock lithological instance classification by hyperspectral images using dimensionality reduction and deep learning. Chemom. Intell. Lab. Syst. 2022, 224, 104538. \nAbstract: The mining operations are part of the industry 4.0 revolution, and there is a need in developing new ways to produce a flow of information among all the processes of a plant. In this context, the lithological classification of the rocks, just after being extracted, provides information related to their chemical composition and physical properties. Hyperspectral imaging is an exceptional tool for acquiring information to perform this characterization. We present a method based on deep learning and hyperspectral images, within the short-wavelength infrared range of 900\u20132500 \u200bnm, to perform lithological classification. The method performs an instance segmentation of the rocks, thus segmenting and classifying the rocks at the same time. A transfer learning methodology was applied by using a deep neural network pretrained with millions of color images to classify the rocks. To use this network, the dimensionality of the hyperspectral images is reduced from 268 to only 3 channels by another neural network. In addition, these 3-channels images can be used for human interpretation. We compare various deep network architectures and classical methods for performing dimensionality reduction. The method was tested on our hyperspectral image database with 13 different lithological classes, obtaining an F1-score that was above 96% and 98% in the instance and pixel-wise performance, respectively.",
        "output": "Galdames et al. (2022) used the mask R-CNN framework to conduct instance segmentation of rocks and achieved high accuracy in classifying certain types of rock.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "He, W.; Ding, Y.; Zi, Y.; Selesnick, I.W. Sparsity-based algorithm for detecting faults in rotating machines. Mech. Syst. Signal Process. 2016, 72\u201373, 46\u201364. \nAbstract: This paper addresses the detection of periodic transients in vibration signals so as to detect faults in rotating machines. For this purpose, we present a method to estimate periodic-group-sparse signals in noise. The method is based on the formulation of a convex optimization problem. A fast iterative algorithm is given for its solution. A simulated signal is formulated to verify the performance of the proposed approach for periodic feature extraction. The detection performance of comparative methods is compared with that of the proposed approach via RMSE values and receiver operating characteristic (ROC) curves. Finally, the proposed approach is applied to single fault diagnosis of a locomotive bearing and compound faults diagnosis of motor bearings. The processed results show that the proposed approach can effectively detect and extract the useful features of bearing outer race and inner race defect.",
        "output": "He et al. (2016) integrated a periodicity-induced OGS (POGS) algorithm into the penalty function to mimic the periodicity of sparse groups for fault detection in rotating machinery.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Fani, A.; Golroo, A.; Mirhassani, S.A.; Gandomi, A.H. Pavement maintenance and rehabilitation planning optimisation under budget and pavement deterioration uncertainty. Int. J. Pavement Eng. 2022, 23, 414\u2013424. \nAbstract: One of the key parts of a pavement management system is the maintenance and rehabilitation planning. The planning is usually developed under the assumption that all parameters are known with certainty. In practice, there are various parameters afflicted with large uncertainty. Ignoring the uncertainty may lead to a suboptimal plan adversely affecting the network conditions. The objective of this study is to develop an optimisation framework for network-level pavement maintenance and rehabilitation planning considering the uncertain nature of pavement deterioration and the budget with an applicable approach. A multistage stochastic mixed-integer programming model is proposed to find the optimal plan that is feasible for all possible scenarios of uncertainty and optimise the expectation of objective function. Two case studies of 4 and 21 pavement sections are presented to show the applicability of the proposed method. The value of stochastic solution and the expected value of perfect information which are the indices for evaluating the benefits of using the stochastic model are, respectively, 30% and 85% of the objective function of here and now model for the first case study and 26% and 42% of it regarding the second one. The indices are high indicating the effectiveness of the stochastic solution.",
        "output": "Fani et al. (2022) discussed the optimization of pavement maintenance and rehabilitation planning under budget and pavement deterioration uncertainties and constructed a multi-stage stochastic mixed-integer programming model.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Dana, L.P.; Salamzadeh, A.; Hadizadeh, M.; Heydari, G.; Shamsoddin, S. Urban entrepreneurship and sustainable businesses in smart cities: Exploring the role of digital technologies. Sustain. Technol. Entrep. 2022, 1, 100016. \nAbstract: The entrance of sustainable and digital technologies into urban entrepreneurship is a new approach that provides a fertile ground for innovation in businesses. Hence, businesses use new models and methods of entrepreneurship in the context of smart cities to increase their capability and become more sustainable, which leads to their development and expansion. This research aims to investigate the effects of urban entrepreneurship on sustainable businesses in smart cities considering the role of digital technologies. The statistical population of this study is all active technology-based firms located in Tehran in 2022. Then, according to Cochran's formula, 315 firms were selected randomly as the sample. This research is an applied and descriptive-survey research and is quantitative in terms of the type of collected data. The data were analysed using Smart PLS 3 software, structural equation modelling (SEM), and the partial least squares methods. As a result, research findings show that urban entrepreneurship creates and develops the studied firms in both quantitative and qualitative aspects by using and benefiting from digital technologies considering the new needs of cities and achieving business sustainability in smart cities.",
        "output": "Dana et al. (2022)  explored the relationship between urban innovation capability and smart city development through a questionnaire survey, considering the role of digital technology. Their findings indicated a bidirectional, positive relationship between smart city development and urban innovation: the construction of smart cities boosts urban innovation capabilities, while the enhancement of these capabilities further contributes to smart city development. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Ezquerro, P., Tom\u00e1s, R., B\u00e9jar-Pizarro, M., Fern\u00e1ndez-Merodo, J. A., Guardiola-Albert, C., Staller, A., et al. (2020). Improving multi-technique monitoring using Sentinel-1 and Cosmo-SkyMed data and upgrading groundwater model capabilities. Sci. Total Environ. 703, 134757. doi:10.1016/j.scitotenv.2019.134757 \nAbstract: Aquifer-systems have become a strategic source of fresh water in the present climatic conditions, especially under stress in arid regions like the Iberian Mediterranean Arc. Understanding the behavior of groundwater reservoirs is crucial to their well-management and mitigation of adverse consequences of overexploitation. In this work, we use space geodetic measurements from satellite interferometric synthetic aperture radar (InSAR) and Global Positioning System (GPS) data, covering the period 2011\u20132017, to predict and validate the ground surface displacement over the fastest subsiding basin due to groundwater withdrawal in Europe (>10\u202fcm/year). The 2D decomposition of InSAR displacements from Cosmo-SkyMed and Sentinel-1 satellites allows us to detect horizontal deformation towards the basin center, with a maximum displacement of 1.5\u202fcm/year. InSAR results were introduced in a newly developed methodology for aquifer system management to estimate unknown pumping rates for the 2012\u20132017 period. This study illustrates how the combination of InSAR data, groundwater flow and deformation models can be used to improve the aquifer-systems sustainable management.",
        "output": "Ezquerro et al. (2020) used Sentinel-1 and CosmoSkyMed satellite data to obtain land subsidence data to calibrate and validate the groundwater model to improve the accuracy and reliability of the groundwater model.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Wang, H.; Zhou, Z.; Zhang, Z.; Zou, Y.; Jiang, J.; Zeng, X. Experimental and numerical studies on shear behavior of prefabricated bridge deck slabs with compact UHPC wet joint. Case Stud. Constr. Mater. 2023, 19, e02362. \nAbstract: Ultra-high performance concrete (UHPC) as a joint material for precast bridge decks might reduce the width of the joint and improve its connection performance and durability. This study proposes a type of compact UHPC wet joint based on the mechanical properties of UHPC and the force characteristics of transverse joints in prefabricated bridge decks. The shear behavior of the novel joint was investigated through experimental study and numerical simulation. In addition, the shear properties of compact UHPC wet joints were compared with epoxy joints. The results indicated that the shear resistances of compact UHPC joints are comparable to those of epoxy joints. The failure process of the precast bridge deck with new joint might be divided into three stages: elastic stage, working stage with cracks, and yield stage. No interface cracks or reinforcement slippage was observed throughout the loading process, indicating that the UHPC joint and the epoxy joint exhibited adequate shear resistance. The ultimate load capacity and corresponding mid-span deflection of UHPC joint specimens were respectively increased by 8.6 % and 75.0 %, when compared with the epoxy joint specimens. Finite element analysis reveals that the transverse shear transfer range of the compact UHPC joints is within 57.1 %. Bending failure due to the yielding of the transverse reinforcement at the bottom of the precast bridge deck is the primary failure mode for both specimens. Moreover, the stresses applied to the deck system have good continuity at the joint.",
        "output": "Wang et al. (2023) proposed a compact UHPC wet joint, and through both experimental and numerical simulation studies, demonstrated that this wet joint variant slightly outperformed the epoxy resin dry joint samples, affirming the wet joint\u2019s superior shear strength, robustness, and adhesion properties.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Yu, B.; Gu, X.; Ni, F.; Guo, R. Multi-objective optimization for asphalt pavement maintenance plans at project level: Integrating performance, cost and environment. Transp. Res. Part D 2015, 41, 64\u201374.  \nAbstract: Traditionally, asphalt pavement maintenance mainly considers pavement performance and cost and largely ignores the environment while substantial amount of environmental burdens are released in the process. In this study, a multi-objective optimization model was developed integrating the three elements in order to optimize the asphalt pavement maintenance plans at the project level. Pavement performance element was decided as the multiplier of pavement serviceability index and traffic volume. Cost element was represented by the net present value, including components of agency cost, vehicle operation cost and salvage value. Environmental element, integrating energy consumption, global warming potential, acidification potential and respiratory effects potential, was measured by the life cycle assessment model. A hypothetic asphalt pavement maintenance case study was conducted using the developed multi-objective optimization model and harvested 103 sets of feasible combinations of maintenance plans, each of which is non-dominated by the others. Trade-offs analysis was performed among the three objectives and visualized in both two- and three-dimension forms. It is found there is an opportunity of reducing the cost and environmental impacts to 80.3% and 77.8% and increasing the pavement performance to 146.6% compared to the base case. However, they are mutually compromised and cannot be reached simultaneously. The developed model reveals the quantitatively interactive relationship of the three objectives and helps optimize the asphalt pavement maintenance plans.",
        "output": "Yu et al. (2015) discussed the multi-objective optimization of project-level pavement maintenance plans, constructing an optimization model integrating pavement performance, costs, and environmental impacts, and designing the corresponding genetic algorithm (GA).",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Kilbourne, W.E.; Polonsky, M.J. Environmental attitudes and their relation to the dominant social paradigm among university students in New Zealand and Australia. Australas. Mark. J. 2005, 13, 37\u201348. \nAbstract: This paper develops a causal model of environmental attitudes using measures of the dominant social paradigm of Western industrial societies. Four components of the DSP framework are examined with regard to environmental attitudes and perception of change using a sample of university students from Australia and New Zealand. The results indicate that one's belief in the DSP has a negative effect on both environmental attitudes and perception of change necessary to ameliorate degradation of the environment. Thus, while public policy favors increasing awareness of and interest in the environment, policy instruments may remain ineffective in producing lasting change if the components of the DSP remain unchanged. It is argued that public policy ought to be directed at changing the DSP so that its negative effects will be minimized.",
        "output": "Kilbourne et al. (2005)  proposed that social norms play an important role in shaping the public\u2019s cognitive framework and attitude towards environmental issues.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Pourakbar, S.; Fasihnikoutalab, M.; Ball, R.; Cristelo, N.; Huat, B. Soil reinforcement through addition and subsequent carbonation of wollasonite microfibres. Geosynth. Int. 2017, 24, 554\u2013564. \nAbstract: This study describes the application of wollasonite microfibres for stabilising soil with the additional function of sequestering CO2. The high aspect ratio, needle-like structure of wollasonite imparted a microfibre mechanical reinforcement whilst the associated high surface area promoted carbonation. The originality of this paper lies in two unique aspects: the first stage assessed the efficacy of incorporating wollastonite microfibres inside the soil mass, while the second stage addressed the mechanical performance of the fibre-reinforced soil after different CO2 pressures and carbonation times. In these two stages, the unconfined compressive strength (UCS), indirect tensile strength (ITS) and flexural strength (FS) were determined. The test results indicated that the inclusion of the fibres increased the peak and post-peak response during unconfined compressive strength (UCS) tests, while also improving the ITS and FS. The UCS peak stress was further improved when the fibre-reinforced soil was subjected to the carbonation process. This work impacts the soil stabilisation industry through a novel soil strengthening process that also promises an effective route to combat climate change through sequestration of CO2.",
        "output": "Pourakbar S. et al. (2017) evaluated the effect of incorporating wollastonite microfibers into soils through UCS, indirect tensile strength (ITS), and flexural strength (FS) tests.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "M.N. Yang, X. Tian, Z.L. Guo, C.P. Chang, J.F. Li, Z.X. Guo, H.R. Li, R.J. Liu, R.D. Wang, Q. Li, X.Y. Zou Wind erosion induced low-density microplastics migration at landscape scale in a semi-arid region of northern China Sci. Total Environ., 871 (2023), Article 162068 \nAbstract: Microplastics (MPs) have been extensively investigated in terrestrial environments, while the occurrence and movement of MPs at the landscape scale in semi-arid regions with serious wind erosion are less well studied. Here, we sampled film mulching farmland and downwind nearby grassland surface soils in a semi-arid region of northern China to explore the distribution of MPs at different downwind distances and the potential environmental risk to the local landscapes. The results revealed that the MP abundances presented a decreasing trend with increasing downwind distance (Mann-Kendall test, P < 0.01). The MP size distributions at different distances showed similar sigmoid trends described by logistic models. MP fiber size (500\u20132000 \u03bcm) abundance in the farmland was higher than that of the grassland. By contrast, MP non-fiber size (<1000 \u03bcm) abundance of farmlands was less than that of the grassland. The abundances of fibers larger than 500 \u03bcm and non-fibers larger than 1000 \u03bcm in size decreased exponentially with increasing downwind distance. The size of transported MPs at the landscape scale was larger than that of long-distance dispersal. The migration of MPs from farmlands can pose a potential threat to the downwind landscape, leading the downwind grassland to be a potential MP emission source. This study presents the first insights into the MPs distribution among different downwind distances at the landscape scale. Future research is required to deploy aeolian sediment sampling devices and establish the connection between the field data and the MP emission models.",
        "output": "As noted by Yang et al. (2023), MP abundances presented a decreasing trend with increasing downwind distance and the size of transported MPs at the landscape scale was larger than that of long-distance dispersal. This means that wind erosion can influence MP distribution and transportation to some extent.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, H.; Liu, T.; Cui, Y.; Wang, Z.; Wang, W.; Zheng, J. Compression and shear properties of OPC-MCA and basalt fiber cured shield waste mud after dry-wet cycles. Constr. Build. Mater. 2024, 426, 136153. \nAbstract: Reinforcing soil with fibers is a useful method for improving the strength and settlement response of soil. The soil and fiber characteristics and their interaction are some of the major factors affecting the strength of reinforced soil. The fibers are usually randomly distributed in the soil, and their orientation has a significant effect on the behavior of the reinforced soil. In the paper, a study of the effect of anisotropic distribution of fibers on the stress-strain response is presented. Based on the concept of the modified Cam clay model, an analytical model was formulated for the fiber-reinforced soil, and the effect of fiber orientation on the stress-strain behavior of soil was studied in detail. The results show that, as the inclination of fibers with the horizontal plane increased, the contribution of fibers in improving the strength of fiber-reinforced soil decreased. The effect of fibers is maximum when they are in the direction of extension, and vice versa.",
        "output": "Zhang et al. (2024) investigated the compression and shear properties of OPC-MCA and basalt fiber-stabilized shield waste sludge after dry\u2013wet cycles, noting that the addition of basalt fiber improved resistance to such cycles.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Kawase, T.; Miyazaki, T.; Kawashima, K. Method for Extracting Intentional Motion Using Force Sensor in Hand-held Robotic Forceps and Its Effect on Performance. Sens. Mater. 2023, 35, 1349. \nAbstract: To enhance the performance of multi-degree-of-freedom hand-held forceps that support\nminimally invasive surgery, it is important to correctly sense the operator\u2019s intended operation\ninput. In our hand-held robotic forceps that use a force sensor as an input device, it was necessary\nto solve the problem of unintended operation input due to gripper operation to move the joint of\nthe forceps. We describe a method for eliminating this unintended input to the interface of the\nhand-held robotic forceps and present the results of an evaluation of its performance. We used a\nvirtual grasp-and-reach task with cursor manipulation of the forceps\u2019 input device in our\nexperiments and evaluated the throughput on the basis of Fitts\u2019 law, which is used to evaluate\nhuman interfaces; the evaluation was based on the results of manipulations by two participants.\nThe results showed that the mean throughput was 1.5 to 2 times higher when the proposed\nprocessing was used. This suggests that the proposed processing of the operational input of the\ninterface contributes to the improvement of performance with the hand-held robotic forceps.",
        "output": "Toshihiro Kawase et al. (2023) investigated the processing of a force sensor-based input device for hand-held robotic tweezers (UIA) to reduce unintended inputs in the tweezers\u2019 tip direction operation due to gripper manipulation.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Julio, E.N.; Branco, F.A.; Silva, V.D. Concrete-to-concrete bond strength. Influence of the roughness of the substrate surface. Constr. Build. Mater. 2004, 18, 675\u2013681. \nAbstract: An experimental study was performed to evaluate the bond strength between two concrete layers, for different techniques for increasing the roughness of the substrate surface. In a total of 25 slant shear specimens and 25 pull-off specimens the substrate surface was prepared by wire-brushing; sand-blasting; chipping with a light jackhammer; or were left as-cast against steel formwork. Three months later, the new concrete was added. Pull-off tests were performed to evaluate the bond strength in tension. Slant shear tests were conducted to quantify the bond strength in shear. Analysis of results indicated that: the highest value of bond strength was achieved with sand-blasting; pull-off tests are adequate to estimate the bond strength in situ; and pre-wetting the substrate surface does not seem to influence the bond strength.",
        "output": "Julio et al. (2004) explored various bond surface treatments, identifying sandblasting as the most effective method to increase bond shear strength, despite its lower construction efficiency; alternatively, keyways proved more practical for routine applications.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhao, Z.; Ji, K.; Xing, X.; Chen, W.; Zou, H. Ship Classification with High Resolution TerraSAR-X Imagery Based on Analytic Hierarchy Process. Int. J. Antennas Propag. 2013, 2013, 698370. \nAbstract: Ship surveillance using space\u2010borne synthetic aperture radar (SAR), taking advantages of high resolution over wide swaths and all\u2010weather working capability, has attracted worldwide attention. Recent activity in this field has concentrated mainly on the study of ship detection, but the classification is largely still open. In this paper, we propose a novel ship classification scheme based on analytic hierarchy process (AHP) in order to achieve better performance. The main idea is to apply AHP on both feature selection and classification decision. On one hand, the AHP based feature selection constructs a selection decision problem based on several feature evaluation measures (e.g., discriminability, stability, and information measure) and provides objective criteria to make comprehensive decisions for their combinations quantitatively. On the other hand, we take the selected feature sets as the input of KNN classifiers and fuse the multiple classification results based on AHP, in which the feature sets\u2019 confidence is taken into account when the AHP based classification decision is made. We analyze the proposed classification scheme and demonstrate its results on a ship dataset that comes from TerraSAR\u2010X SAR images.",
        "output": "Zhao et al. (2013) employed a hierarchical analysis method, utilizing a feature set comprising geometric, transformational, and local invariant features, to identify the most effective feature subset. They then leveraged a K-Nearest Neighbor (KNN) classifier to achieve successful classification of cargo ships, oil tankers, and container ships from TerraSAR-X imagery.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Marzban, J.; Ghaseminejad, P.; Ahmadzadeh, M.H.; Teimouri, R. Experimental investigation and statistical optimization of laser surface cladding parameters. Int. J. Adv. Manuf. Technol. 2015, 76, 1163\u20131172. \nAbstract: In laser surface cladding process, the formed clad geometry is directly affected by laser cladding parameters like laser power, scan speed, and powder feed rate. Therefore, finding an optimal parameter setting to increase the process performance is crucial. In the present study, experimental investigation on laser cladding process of AISI 1040 has been performed. Here, numbers of nine experiments were designed and conducted based on L9 orthogonal array design to study effects of mentioned factors on clad height, clad width, and clad depth. Then the principal component analysis (PCA) was integrated with TOPSIS method for multiresponses optimization of laser cladding process. Here, the PCA was used to find appropriate weight factor related to each quality characteristic. Hereafter, the technique for order preference by similarity to ideal solution (TOPSIS) was utilized to find optimal solutions. Confirmatory experiments were carried out to validate optimal results. Results revealed that the laser power has greatest influence on laser cladding quality characteristics. Furthermore, results which were obtained through of confirmatory experiments reveal that the developed method can effectively acquire the optimal combination of laser cladding parameters.",
        "output": "Marzban et al. (2015) conducted an orthogonal laser cladding experiment on the surface of AISI 1040 steel and optimized the processing parameters through principal component analysis and approximate ideal solution ordering. Their findings revealed that the laser power exerts the most significant influence on the quality of the cladding.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Qin, M.; Qin, P.; Qin\u00b7 Jiang, Y.; Guo, J.; Zhang, G.; Ramzan, M. Occurrence of shallow landslides triggered by increased hydraulic conductivity due to tree roots. Landslides 2022, 19, 2593\u20132604. \nAbstract: Vegetation is widely recognized as a key factor controlling the occurrence of shallow landslides in vegetation-covered areas. In such areas, the root system plays a critical role both in enhancing root-soil mechanical properties and in changing soil hydrological properties. However, owing to its complexity and nonuniformity, the root system is always neglected or simplified in existing infiltration process models, making it difficult for such models to reflect the influence of root systems on shallow landslides. Considering the shallow landslide cluster that happened in Mengdong (Yunnan Province, Southwest China) in 2018, this study quantitatively investigated the root distribution and obtained the prevailing physical and hydraulic properties through density tests, shear strength tests, and saturated seepage tests. Field investigation indicated that the root system distribution obeys an exponentially decayed polynomial model. In the entire profile, the maximum root area density was 0.145 mm2 cm\u22122 at depth of 20\u201340 cm, which comprised 483 roots, and 80% of the roots were distributed above the slip surface. Laboratory test results indicated that root-soil above the slip surface had lower density (minimum density: 1.04 g cm\u22123) and higher porosity (maximum porosity: 61.23%) than soil below, which induced permeability 10\u201317 times higher above the slip surface. A potential relationship was found between slip surface location and root system distribution. Differences in root distribution and resultant changes in the hydrological properties of soil might reduce slope stability during extreme rainfall, which could induce shallow landslides. This research could be used as reference for slope stability and hydraulic process analysis in forested areas.",
        "output": "Qin et al. (2022) denoted that the macropore network system formed by rotten root channels might include entire hillslopes and provide a rapid drainage path for water following rainfall.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, T.; Gong, L.; Wang, S.; Zuo, S. Hand-held instrument with integrated parallel mechanism for active tremor compensation during microsurgery. Ann. Biomed. Eng. 2020, 48, 413\u2013425. \nAbstract: Physiological hand tremor seriously influences the surgical instrument\u2019s tip positioning accuracy during microsurgery. To solve this problem, hand-held active tremor compensation instruments are developed to improve tip positioning accuracy during microsurgery. This paper presents the design and performance of a new hand-held instrument that aims to stabilize hand tremors and increase accuracy in microsurgery. The key components are a three degrees of freedom (DOF) integrated parallel manipulator and a high-performance inertial measurement unit (IMU). The IMU was developed to sense the 3-DOF motion of the instrument tip. A customized filter was applied to extract specific hand tremor motion. Then, the instrument was employed to generate the reverse motion simultaneously to reduce tremor motion. Experimental results show that the tremor compensation mechanism is effective. The average RMS reduction ratio of bench test is 56.5% that is a significant tremor reduction ratio. For hand-held test, it has an average RMS reduction ratio of 41.0%. Hence, it could reduce hand tremor magnitudes by 31.7% RMS in 2-DOF.",
        "output": "Tianci Zhang et al. (2020) developed a hand-held active tremor compensation instrument to improve tip positioning accuracy in microsurgery, and the experimental results showed that for the hand-held test, the average RMS (effective value) reduction ratio was 41.0%.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Li, J.; Qu, C.; Peng, S. Ship classification for unbalanced SAR dataset based on convolutional neural network. J. Appl. Remote. Sens. 2018, 12, 035010. \nAbstract: Ship classification in synthetic aperture radar (SAR) images is essential in remote sensing but still full of challenges in the deep learning era. The unbalanced dataset and lack of models are two limitations. Upsampling with data augmentation and ratio batching are proposed to solve the first problem. Upsampling with data augmentation is upsampling by cropping and flipping. It can improve the diversity of the dataset. Ratio batching is realized by choosing the same amount of ships per class in each minibatch. It can make the model converge faster and better. To solve the second problem, a new loss function and convolutional neural network model are proposed. The new loss function can maximize the intraclass compactness and interclass separation simultaneously. Dense residual network has two submodules. One is the identity mapping through elementwise summation to reuse old features. The other is dense connection through concatenation to exploit new features. The designed architecture is suitable for the task of SAR ship classification. We use the confusion matrix and accuracy averaged on classes to measure the performance. From the experiments, we can find that the proposed ideas have excellent performance especially on the rare classes.",
        "output": "Li et al. (2018) developed a dense residual network (DRNet) incorporating upsampling data augmentation and in-batch balanced sampling to address the challenge of class imbalance in ship classification. They validated the efficacy of their approach on the publicly available OpenSARShip dataset. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Christiansen, J.S.; Thorsen, M.; Clausen, T.; Hansen, S.; Refsgaard, J.C. Modelling of macropore flow and transport processes at catchment scale. J. Hydrol. 2004, 299, 136\u2013158. \nAbstract: Macropores play a significant role as a preferential flow mechanism in connection with pesticide leaching to shallow groundwater in clayey and loamy soils. A macropore description based on some of the same principles as those of the MACRO code has been added to the coupled MIKE SHE/Daisy code, enabling a physically based simulation of macropore processes in a spatially distributed manner throughout an entire catchment. Simulation results from a small catchment in Denmark suggest that although the point scale macropore processes have no dominating effect on groundwater recharge or discharge at a catchment scale, they will have significant effects on pesticide leaching to groundwater at a catchment scale. The primary function of macropores in this area is that they rapidly transport a significant part of the infiltrating water and solutes from the plough pan at 20 cm depth some distance downwards before most of it flows back into the soil matrix. This has a very significant effect on the leaching of pesticides from the surface to the groundwater table, because some of the pesticides are transported rapidly downwards in the soil profile to zones with less sorption and degradation. It is concluded that the spatial variations of macropore flows caused by the variation in topography and depth to groundwater table within a catchment are so large that this has to be accounted for in up-scaling process descriptions and results from point scale to catchment scale.",
        "output": "Christiansen et al. (2004) simulated the macropore flow and transport processes at the catchment scale and noted that macropores could rapidly transport most of the infiltrating water and solutes from the plough pan at a 20 cm depth some distance downwards before it flowed back into the soil matrix.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Kanchi, G.M.; Neeraja, V.S.; Babu, G.L.S. Effect of Anisotropy of Fibers on the Stress-Strain Response of Fiber-Reinforced Soil. Int. J. Geomech. 2014, 15, 06014016. \nAbstract: Reinforcing soil with fibers is a useful method for improving the strength and settlement response of soil. The soil and fiber characteristics and their interaction are some of the major factors affecting the strength of reinforced soil. The fibers are usually randomly distributed in the soil, and their orientation has a significant effect on the behavior of the reinforced soil. In the paper, a study of the effect of anisotropic distribution of fibers on the stress-strain response is presented. Based on the concept of the modified Cam clay model, an analytical model was formulated for the fiber-reinforced soil, and the effect of fiber orientation on the stress-strain behavior of soil was studied in detail. The results show that, as the inclination of fibers with the horizontal plane increased, the contribution of fibers in improving the strength of fiber-reinforced soil decreased. The effect of fibers is maximum when they are in the direction of extension, and vice versa.",
        "output": "Kanchi M. G. et al. (2014) developed an analytical model for fiber-reinforced soil based on the modified Cambridge model, investigating in detail the effect of fiber orientation on the soil\u2019s stress\u2013strain characteristics. The results showed that fibers had the greatest effect in the extension direction. The contribution of fibers to the strength of fiber-reinforced soil decreases as the angle of inclination of the fibers to the horizontal increases.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Sun, Y.; Hu, M.; Zhou, W.; Xu, W. Multiobjective optimization for pavement network maintenance and rehabilitation programming: A case study in Shanghai, China. Math. Probl. Eng. 2020, 2020, 3109156. \nAbstract: This study investigates the pavement network maintenance and rehabilitation (M&R) programming problem, over a certain planning horizon and in the context of limited funding. We designed an integer programming model to fulfill three purposes, namely, optimize the road conditions, minimize user disturbance costs, and minimize agency costs. We present a case study in which this model is applied to the pavement network of Shanghai. We investigate the results through the use of five M&R strategies, to identify the Pareto-optimal trade-offs inherent in developing pavement network M&R planning. The results demonstrate that there is a positive relationship between PCI improvement and user disturbance costs and between PCI improvement and agency costs. Additionally, we conduct a comparative analysis between agency and government-oriented strategies to evaluate the effectiveness and equity consideration. The findings suggest that the government-oriented strategy improves the pavement condition effectively with low user disturbance costs, and the agency-oriented strategy accounts for more equity consideration. Finally, we formulate an extension model that considers multiple road types, for application to pavement network M&R programming. The results show that light rehabilitation and preventive maintenance are the most frequently implemented treatments on arterial roads and secondary trunk roads from the case network implementation. This study helps decision-makers identify the trade-offs made when developing a pavement network M&R program.",
        "output": "Sun et al. (2020) discussed the multi-objective optimization problem of network-level pavement maintenance and rehabilitation programming, constructing an integer programming model to optimize road conditions, user disruption costs, and agency costs, and proposing a Pareto-based optimal trade-off method.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Grace, N.; Abdei-Sayed, G. Behavior of Externally Draped CFRP Tendons in Prestressed Concrete Bridges. PCI J. 1998, 43, 88\u2013101. \nAbstract: Successful use of carbon fiber reinforced polymer (CFRP) tendons in prestressed concrete bridges can be achieved by combining bonded internal tendons with unbonded externally draped tendons. To examine this theory, four bridge models were tested under static, repeated (7 million cycles), and ultimate loads. Also, the combined effects of factors such as:(a) draping angle;(b) deviator diameter;(c) number of attached die-casts used to anchor the tendons;(d) presence of cushioning material between the deviator and the tendon; and (e) twist angle on the strength of the tendons were examined. It was concluded that the use of externally draped CFRP tendons in bridge construction improves ductility and forces the concrete to undergo inelastic deformation resulting in compression failure. It is also noted that increasing the deviator diameter and using cushioning material at the deviators minimize the reduction in the breaking force of the draped tendon.",
        "output": "In a comprehensive experimental research work, Grace et al. (1998) evaluated the static and fatigue performance of bridges reinforced with bonded internal CFRP tendons and unbonded external CFRP tendons. This experiment considered various factors, including the draping angle, deviator diameter, number of attached die-casts, etc. The prestress loss of the external unbonded CFRP tendons was found to be less than 7%, and the ductility of the reinforced bridge significantly improved at failure. Furthermore, they emphasized the importance of incorporating measures in deviator design to reduce the stress concentration on the CFRP tendons.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Ma, N., Sun, W., Wang, Z., Li, H., Ma, X., and Sun, H. (2023). The effects of different forms of FDI on the carbon emissions of multinational enterprises: a complex network approach. Energy Policy 181, 113731. doi:10.1016/j.enpol.2023.113731 \nAbstract: The carbon emissions of multinational enterprises (MNEs) through FDI are causing a shift in the emissions burden and threatening mitigation targets. The purpose of this paper is to investigate the effects of the FDI stock, greenfield FDI, and M&As on carbon emissions of MNEs from 2005 to 2016 via quadratic assignment procedure (QAP) network analysis. Through QAP network analysis, we study the FDI-carbon emissions linkage considering the interactions among agents. The results show that the \u201chigh-income region to low-income region\u201d mode is gradually becoming the driving force in the global carbon flow, producing lots of carbon emissions with a lower investment. The investments in this mode are dirtier. Second, financial institutions have become the key emitters of global carbon emissions through FDI. This investment model makes global carbon transfer indirect and concealed. Third, the significance of the impacts of the three forms of FDI on the carbon emissions of MNEs is positive, which confirms the pollution haven effect. The greatest contributor is the FDI stock, which comes from historical investments in high-income regions. Greenfield FDI is more influential than M&As in both high- and low-income regions. This paper is a valuable reference for understanding the environmental effects of FDI.",
        "output": "Ma et al. (2023), using QAP network analysis, found a strong correlation between FDI networks and the carbon emissions networks of multinational companies, with investment patterns from high-income areas more likely to lead to significant carbon emissions in low-income areas (Ma et al., 2023).",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Middel, A.; H\u00e4b, K.; Brazel, A.J.; Martin, C.A.; Guhathakurta, S. Impact of Urban Form and Design on Mid-Afternoon Microclimate in Phoenix Local Climate Zones. Landsc. Urban Plan. 2014, 122, 16\u201328. \nAbstract: This study investigates the impact of urban form and landscaping type on the mid-afternoon microclimate in semi-arid Phoenix, Arizona. The goal is to find effective urban form and design strategies to ameliorate temperatures during the summer months. We simulated near-ground air temperatures for typical residential neighborhoods in Phoenix using the three-dimensional microclimate model ENVI-met. The model was validated using weather observations from the North Desert Village (NDV) landscape experiment, located on the Arizona State University's Polytechnic campus. The NDV is an ideal site to determine the model's input parameters, since it is a controlled environment recreating three prevailing residential landscape types in the Phoenix metropolitan area (mesic, oasis, and xeric). After validation, we designed five neighborhoods with different urban forms that represent a realistic cross-section of typical residential neighborhoods in Phoenix. The scenarios follow the Local Climate Zone (LCZ) classification scheme after Stewart and Oke. We then combined the neighborhoods with three landscape designs and, using ENVI-met, simulated microclimate conditions for these neighborhoods for a typical summer day. Results were analyzed in terms of mid-afternoon air temperature distribution and variation, ventilation, surface temperatures, and shading. Findings show that advection is important for the distribution of within-design temperatures and that spatial differences in cooling are strongly related to solar radiation and local shading patterns. In mid-afternoon, dense urban forms can create local cool islands. Our approach suggests that the LCZ concept is useful for planning and design purposes.",
        "output": "Middel et al. (2014) investigated the effects of urban form and landscape design on mid-afternoon microclimates, demonstrating how different urban forms and landscaping can influence local temperature and comfort conditions.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Cho, S.; Lee, H.; Chung, W. Strengthening Effect of Prestressed Near-Surface Mounted CFRP Bar System According to Material Properties of Aged Reinforced Concrete Beams. Compos. Struct. 2022, 282, 115121. \nAbstract: The flexural performance improvement of age-deteriorated reinforced concrete (RC) beams by a near-surface mounted carbon fiber-reinforced polymer (NSM CFRP) bar system was experimentally investigated. Ten 6.4 m long RC beams were fabricated and tested in four-point bending using different concrete compressive strengths to distinguish between old and new concrete, different steel reinforcement ratios to reflect deterioration with age, and different quantities of prestressed and non-prestressed CFRP bars. The results indicated that the ultimate strengths of the NSM CFRP-strengthened RC beams were up to twice that of the un-strengthened control beam, and the strengthening effect increased with the material properties of the RC beam. A finite element model of the strengthened RC beam was constructed and verified against the experimental results, then used to conduct a parametric study of the influence of the concrete compressive strength and steel reinforcement ratio on the strengthening effect of the prestressed NSM CFRP bar system.",
        "output": "A finite element (FE) model was used by Cho et al. (2022) to conduct a parametric study. The model precision was validated using test outcomes. The errors of the cracking, yielding and ultimate loads between the numerical and experimental results were within 9%.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zheng P., Xu Q., Luo X., Zheng Z., Zheng W., Chen X., Zhou Z., Yan Y., Zhang H. Aeolus: Distributed execution of permissioned blockchain transactions via state sharding IEEE Trans. Ind. Inform., 18 (2022), pp. 9227-9238 \nAbstract: Blockchain has attracted lots of attention in recent years. However, the performance of blockchain cannot meet the requirement of massive Internet of Things (IoT) devices. One of the important bottlenecks of blockchain is the limited computing resources on a single server while executing transactions. To address this issue, we propose Aeolus blockchain to achieve the distributed execution of blockchain transactions. There are two key challenges to achieving this for IoT blockchain: transaction structure and state consistency. Facing these challenges, we first propose a distributed blockchain transaction structure, which imports extra parameters to divide the transaction execution into different stages to enable distributed execution. Second, we propose distributed state update sharding, which equips each blockchain peer with its own master and shard servers. In this way, each blockchain peer can be considered as a cluster that distributes the transaction to shorten the processing time and reach the consensus finally. We implement Aeolus on Go-Ethereum to evaluate its feasibility, on a testbed including 132 cloud servers. Our system runs stably for more than 8 h under the workload of 190 000 000 real-world user transactions. Experimental results show the efficiency that Aeolus can achieve more than 100 000 transactions/s of blockchain transactions, which is 15.6 times the throughput of the original blockchain.",
        "output": "To address the performance bottlenecks in exciting sharded blockchain systems, Zheng et al. (2022) proposed a distributed blockchain transaction structure that divides transactions into different stages for distributed execution. This approach shortens processing time through transaction allocation to improve blockchain throughput.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Shamass, R.; Zhou, X.; Wu, Z. Numerical analysis of shear-off failure of keyed epoxied joints in precast concrete segmental bridges. J. Bridge Eng. 2017, 22, 04016108. \nAbstract: Precast concrete segmental box girder bridges (PCSBs) are becoming increasingly popular in modern bridge construction. The joints in PCSBs are of critical importance, which largely affects the overall structural behavior of PCSBs. The current practice is to use unreinforced small epoxied keys distributed across the flanges and webs of a box girder cross section forming a joint. In this paper, finite-element analysis was conducted to simulate the shear behavior of unreinforced epoxied joints, which are single keyed and three keyed to represent multikeyed epoxied joints. The concrete damaged plasticity model along with the pseudodamping scheme was incorporated to analyze the key assembly for microcracks in the concrete material and to stabilize the solution, respectively. In numerical analyses, two values of concrete tensile strength were adapted: one using a Eurocode formula and one using the general assumption of tensile strength of concrete as 10%fcm. The epoxy was modeled as linear elastic material because the tensile and shear strength of the epoxy were much higher than those of the concrete. The numerical model was calibrated by full-scale experimental results from literature. Moreover, it was found that the numerical results of the joints, such as ultimate shear load and crack initiation and propagation, agreed well with experimental results. Therefore, the numerical model associated with relevant parameters developed in this study was validated. The numerical model was then used for a parametric study on factors affecting shear behavior of keyed epoxied joints, which are concrete tensile strength, elastic modulus of epoxy, and confining pressure. It has been found that the tensile strength of concrete has a significant effect on the shear capacity of the joint and the displacement at the ultimate load. A linear relationship between the confining pressure and the shear strength of single-keyed epoxied joints was observed. Moreover, the variation in the elastic modulus of epoxy does not affect the ultimate shear strength of the epoxied joints when it is greater than 25% of the elastic modulus of concrete. Finally, an empirical formula published elsewhere for assessing the shear strength of single-keyed epoxied joints was modified, based on the findings of this research, to be an explicit function of the tensile strength of concrete.",
        "output": "Regarding the effect of confining pressure on the shear strength, Shamass et al. (2017) utilized the ABAQUS finite element software tool to model pre-cast concrete segmental box girder bridge nodes, identifying a linear correlation between the perimeter stress and the shear force of epoxy joints. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Mahmoud, R., Hassanin, M., Al Feel, H., and Badry, R. M. (2023). Machine learning-based land use and land cover mapping using multi-spectral satellite imagery: A case study in Egypt. Sustainability. 15 (9467), 1\u201321. doi:10.3390/su15129467 \nAbstract: Satellite images provide continuous access to observations of the Earth, making environmental monitoring more convenient for certain applications, such as tracking changes in land use and land cover (LULC). This paper is aimed to develop a prediction model for mapping LULC using multi-spectral satellite images, which were captured at a spatial resolution of 3 m by a 4-band PlanetScope satellite. The dataset used in the study includes 105 geo-referenced images categorized into 8 LULC different classes. To train this model on both raster and vector data, various machine learning strategies such as Support Vector Machines (SVMs), Decision Trees (DTs), Random Forests (RFs), Normal Bayes (NB), and Artificial Neural Networks (ANNs) were employed. A set of metrics including precision, recall, F-score, and kappa index are utilized to measure the accuracy of the model. Empirical experiments were conducted, and the results show that the ANN achieved a classification accuracy of 97.1%. To the best of our knowledge, this study represents the first attempt to monitor land changes in Egypt that were conducted on high-resolution images with 3 m of spatial resolution. This study highlights the potential of this approach for promoting sustainable land use practices and contributing to the achievement of sustainable development goals. The proposed method can also provide a reliable source for improving geographical services, such as detecting land changes.",
        "output": "Studies in Egypt have demonstrated the effectiveness of various ML algorithms, such as Support Vector Machines (SVMs), Decision Trees (DTs), Random Forests (RFs), and Artificial Neural Networks (ANNs), in utilizing multi-spectral satellite imagery for precise LULC mapping (Mahmoud et al., 2023). ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Huang H., Peng X., Zhan J., Zhang S., Lin Y., Zheng Z., Guo S. Brokerchain: A cross-shard blockchain protocol for account/balance-based state sharding IEEE INFOCOM 2022-IEEE Conference on Computer Communications, IEEE (2022), pp. 1968-1977 \nAbstract: State-of-the-art blockchain sharding solutions, say Monoxide, can induce imbalanced transaction (TX) distributions among all blockchain shards due to their account deployment mechanisms. Imbalanced TX distributions then cause hot shards, in which the cross-shard TXs may experience an unlimited length of confirmation latency. Thus, how to address the hot-shard issue and how to reduce cross-shard TXs become significant challenges of blockchain state sharding. Through reviewing the related studies, we find that a cross-shard TX protocol that can achieve workload balance among all shards and simultaneously reduce the number of cross-shard TXs is still absent from the literature. To this end, we propose BrokerChain, which is a cross-shard blockchain protocol devised for the account/balance-based state sharding. Essentially, BrokerChain exploits fine-grained state partition and account segmentation. We also elaborate on how BrokerChain handles cross-shard TXs through broker accounts. The security issues and other properties of BrokerChain are analyzed substantially. Finally, we conduct comprehensive evaluations using both a cloud-based prototype and a transaction-driven simulator. The evaluation results show that BrokerChain outperforms other solutions in terms of system throughput, transaction confirmation latency, the queue size of transaction pool, and workload balance.",
        "output": "Huang et al. (2022) proposed a fine-grained state-sharding mechanism called \u201cBrokerchain\u201d which utilizes broker accounts to convert cross-shard transactions into two intra-shard transactions, reducing the volume of cross-shard transactions to a certain extent. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Vinodha K., Jayashree R., Kommineni G., Tanna M., Prerna G. Sharding in blockchain systems: Concepts and challenges 2022 International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON, IEEE (2022), pp. 1-7 \nAbstract: Due to the persistent issue of blockchain scala-bility, sharding was established as a database splitting approach utilized by blockchain systems to improve scalability. Sharding in blockchain systems presents several challenges, including security, cross-shard communication, and scalability. A significant quantity of study has been conducted in these sub-areas. However, no new research has been conducted that looks deeper into the issues in each area. This survey provides a concise overview of current concepts and challenges in sharded blockchain systems. We explore distributed systems, blockchain technology, sharding and related concepts. We analyzed 14 papers and divided the findings into two categories: concepts and challenges. The following is how the paper is organized: The first section introduces the concepts of sharding, distributed systems, and blockchain technology, the following sections discuss the challenges and relevant algorithms. Finally, we compare the challenges to present results.",
        "output": "Meanwhile, the existing sharding schemes lead to limited performance enhancement of the system due to the high cross-shard ratio, which can be seen as an essential problem to be solved in the current blockchain partitioning mechanism (Vinodha et al., 2022).",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Wu, J.; Zhu, Y.; Wang, Z.; Song, Z.; Liu, X.; Wang, W.; Zhang, Z.; Yu, Y.; Xu, Z.; Zhang, T.; et al. A novel ship classification approach for high resolution SAR images based on the BDA-KELM classification model. Int. J. Remote Sens. 2017, 38, 6457\u20136476. \nAbstract: Ship classification based on synthetic aperture radar (SAR) images is a crucial component in maritime surveillance. In this article, the feature selection and the classifier design, as two key essential factors for traditional ship classification, are jointed together, and a novel ship classification model combining kernel extreme learning machine (KELM) and dragonfly algorithm in binary space (BDA), named BDA-KELM, is proposed which conducts the automatic feature selection and searches for optimal parameter sets (including the kernel parameter and the penalty factor) for classifier at the same time. Finally, a series of ship classification experiments are carried out based on high resolution TerraSAR-X SAR imagery. Other four widely used classification models, namely k-Nearest Neighbour (k-NN), Bayes, Back Propagation neural network (BP neural network), Support Vector Machine (SVM), are also tested on the same dataset. The experimental results shows that the proposed model can achieve a better classification performance than these four widely used models with an classification accuracy as high as 97% and encouraging results of other three multi-class classification evaluation metrics.",
        "output": "Wu et al. (2017) delved into the joint optimization of feature selection and classifier design, proposing a BDA-KELM algorithm that automatically performs feature selection and parameter optimization to determine the optimal feature\u2013classifier combination.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Hamedianfar, A.; Laakso, K.; Middleton, M.; T\u00f6rm\u00e4nen, T.; K\u00f6ykk\u00e4, J.; Torppa, J. Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods. Remote Sens. 2023, 15, 4806. \nAbstract: Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000\u201312,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.",
        "output": "Hamedianfar et al. (2023) used a deep learning framework with a U-net architecture called ENVINet5 to conduct precise pixel-wise classification, which improved the mineral category classification and captured subtle features. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Chen, P.Y.; Selesnick, I.W. Translation-invariant shrinkage/thresholding of group sparse signals. Signal Process. 2014, 94, 476\u2013489. \nAbstract: This paper addresses signal denoising when large-amplitude coefficients form clusters (groups). The L1-norm and other separable sparsity models do not capture the tendency of coefficients to cluster (group sparsity). This work develops an algorithm, called \u2018overlapping group shrinkage\u2019 (OGS), based on the minimization of a convex cost function involving a group-sparsity promoting penalty function. The groups are fully overlapping so the denoising method is translation-invariant and blocking artifacts are avoided. Based on the principle of majorization\u2013minimization (MM), we derive a simple iterative minimization algorithm that reduces the cost function monotonically. A procedure for setting the regularization parameter, based on attenuating the noise to a specified level, is also described. The proposed approach is illustrated on speech enhancement, wherein the OGS approach is applied in the short-time Fourier transform (STFT) domain. The OGS algorithm produces denoised speech that is relatively free of musical noise.",
        "output": "Chen and Selesnick (2014) further introduced non-convex regularization terms to make the total cost function convex, enhancing its performance under sparsity and refining the OGS algorithm. Unlike traditional sparse denoising methods, which treat each coefficient independently, OGS considers groups of coefficients. This grouping helps to preserve the relationships between signal components, which is crucial for accurately recovering the underlying signal structure.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Elhadidy, A.A.; Elbeltagi, E.E.; Ammar, M.A. Optimum analysis of pavement maintenance using multi-objective genetic algorithms. HBRC J. 2015, 11, 107\u2013113. \nAbstract: Road network expansion in Egypt is considered as a vital issue for the development of the country. This is done while upgrading current road networks to increase the safety and efficiency. A pavement management system (PMS) is a set of tools or methods that assist decision makers in finding optimum strategies for providing and maintaining pavements in a serviceable condition over a given period of time. A multi-objective optimization problem for pavement maintenance and rehabilitation strategies on network level is discussed in this paper. A two-objective optimization model considers minimum action costs and maximum condition for used road network. In the proposed approach, Markov-chain models are used for predicting the performance of road pavement and to calculate the expected decline at different periods of time. A genetic-algorithm-based procedure is developed for solving the multi-objective optimization problem. The model searched for the optimum maintenance actions at adequate time to be implemented on an appropriate pavement. Based on the computing results, the Pareto optimal solutions of the two-objective optimization functions are obtained. From the optimal solutions represented by cost and condition, a decision maker can easily obtain the information of the maintenance and rehabilitation planning with minimum action costs and maximum condition. The developed model has been implemented on a network of roads and showed its ability to derive the optimal solution.",
        "output": "Elhadidy et al. (2015) constructed a performance prediction model based on the Markov chain model, focusing on maximizing the overall condition of the road network while minimizing maintenance and renovation costs.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, W.; Jiao, L.; Li, Y.; Huang, Z.; Wang, H. Laplacian feature pyramid network for object detection in VHR optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 2021, 60, 5604114.  \nAbstract: Except for multiscale features, high-frequency features are also crucial for the identification of many objects in object detection for very high resolution optical remote sensing (VHR-ORS) images but have not been considered yet. Due to the fact that the Laplacian pyramid consists of high-frequency information at each level, we propose a Laplacian feature pyramid (FP) network (LFPN) considering both low-frequency features and high-frequency features based on FP structure to improve the object detection performance of VHR-ORS images. FP-based structures are efficient to represent multiscale features. But, in general, FP-based structures, high-frequency features are not specially considered. Such high-frequency features are important to distinguish many ground objects with sufficient details. For example, texture features are critical to distinguish basketball_court and tennis_court. The construction of LFPN consists of a bottom-up pathway, Laplacian pathway, and a fusion pathway, which generate low-frequency pyramid, high-frequency pyramid, and compound pyramid, respectively. The bottom-up pathway follows the computation flow of the backbone convolutional neural networks (CNNs) which is similar to general FP-based structures. The Laplacian pathway extracts the high-frequency features of objects through a trainable Laplacian operator. Finally, the low-frequency and high-frequency FPs are fused to generate the compound pyramid in efficient ways. To evaluate the performance of LFPN, we embed LFPN into both two-stage object detection (T-LFPN) systems and single-stage object detection (S-LFPN) systems to conduct experiments. Experiments on a public challenging ten-class data set NWPU VHR-10 demonstrate the superior performance of LFPN in both T-LFPN and S-LFPN systems and state-of-the-art performance of LFPN-based detectors.",
        "output": "Zhang et al. (2021) proposed a Laplacian feature pyramid network (LFPN), integrating high-frequency information into the multi-scale pyramid feature representation, thus enhancing the accuracy of object detection. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Ye, T., Xie, Q., Wang, Y., An, Y., and Jin, J. (2018). Analog modeling of sand slope stability with different precipitation conditions. J. Mod. Transp. 26 (3), 200\u2013208. doi:10.1007/s40534-018-0163-0 \nAbstract: Water-sand flow triggered by rainfall is the dominant mechanism for instability and failure of sand slopes. To further analyze the stability state of sand on a slope under different rainfall conditions, the initiation conditions and flow characteristics of water-sand flows are studied. Based on the theory of equilibrium forces and hydrological dynamics, a 1:100-scale analog model is built and verified with field observation data. The results indicate three dynamic stabilization stages of the sand slope under different weather conditions: dry sand, wet sand, and water-sand flow. Water-sand flows are triggered easily under short duration and heavy rainfall conditions. The rainfall threshold required to initiate water-sand flow is 4.14 mm/h. Rainfall amount and duration required to initiate water-sand flow decrease with fine sand content increasing. A sand head that develops at the front of the water-sand flow results in a flow along the edge of the sand debris flow and a tree root flow morphology. Modeling results are consistent with theoretical analysis and field observations.",
        "output": "To further investigate the stability state of the slope under different rainfall conditions, Ye et al. (2018) built a 1:100 scale analog model that was verified with field survey results, and they identified three kinetic stages of sand slope, i.e., dry sand, wet sand, and water-sand flow. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Tran, D.T.; Pham, T.M.; Hao, H.; Chen, W. Numerical Investigation of Flexural Behaviours of Precast Segmental Concrete Beams Internally Post-Tensioned with Unbonded FRP Tendons Under Monotonic Loading. Eng. Struct. 2021, 249, 113341. \nAbstract: This study numerically examines the prospects of replacing steel tendons with fibre reinforced polymer (FRP) tendons in precast segmental concrete girders/beams (PSCBs) for mitigating the corrosion damage to precast structures using finite element (FE) software Abaqus. This is the first study in the published literature that successfully builds an experimentally-verified 3D FE model of dry-joined PSCBs internally prestressed with unbonded FRP tendons to thoroughly investigate the beam\u2019s flexural behaviour. The effect of segments\u2019 interface imperfection on the initial stiffness of PSCBs was successfully captured in this study. The distinguished working mechanisms between monolithic and segmental beams, and between FRP and steel tendons in both tension- and compression-governed cases were comprehensively discussed. An intensive parametric study was also conducted to examine the effect of primary parameters (effective prestressing stress, prestressing reinforcement amount, span-to-depth ratio and different types of FRP tendons) on the flexural response of PSCBs. The results have proven that commonly available CFRP tendons (Young\u2019s modulus Ep = 145 GPa) can well replace steel tendons in PSCBs while high-modulus CFRP tendons (Ep = 200 GPa) should be used with caution to ensure the PSCBs can achieve sufficient deformability. Moreover, among some existing models, ACI 440.4R-04\u2032s model gave the most accurate predictions of the ultimate stress of unbonded FRP tendons (fpu) in PSCBs compared to the numerical results but its estimation was slightly unconservative and scattered. A new bond reduction factor was, hence, proposed for better prediction of fpu of FRP tendons in PSCBs. The ultimate stress of unbonded FRP tendons in PSCBs should be limited to 75% of the tensile strength of the tendon in design to account for the deformation concentration at the joints and the brittle failure characteristics of FRP tendons.",
        "output": "Tran et al. (2021) numerically investigated the bending response of dry key-jointed precast segmental concrete beams prestressed with external FRP tendons. The model validated by tests was used to conduct an intensive parametric analysis with a focus on the second-order effect.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Liu, X.; Yu, W.; Huang, Y.; Yang, G.; You, W.; Gao, L. Long-Term Behaviour of Recycled Aggregate Concrete Beams Prestressed with Carbon Fibre-Reinforced Polymer (CFRP) Tendons. Case Stud. Constr. Mater. 2023, 18, e01785. \nAbstract: The utilisation of recycled aggregate concrete (RAC) is commonly recognised as one of the most effective means to achieve cleaner and sustainable development in civil engineering. To promote the application of RAC, prestressing technique can be employed to overcome the inherent disadvantages of RAC beams associated with poor cracking resistance and large deflections. However, the research on the prestressed RAC beam is quite limited, and no research has been performed on their long-term behaviour. This paper presents a finite element (FE) analysis for investigating the long-term behaviour of RAC beams prestressed with carbon fibre-reinforced polymer (CFRP) tendons considering the effects of concrete creep, concrete shrinkage, tendon relaxation as well as the cracking and tension stiffening of concrete. Based on the principle of superposition, the variations of the stress and strain with time are considered in the numerical analysis using step-by-step method. The FE model is calibrated with the experimental results obtained from the literature. Based on the validated model, a comprehensive parametric study is performed to investigate the effects of the replacement ratio of recycled coarse aggregate (RCA), concrete strength, reinforcement ratio, prestress level, and sustained load level on the long-term behaviour of prestressed RAC beams. The obtained results demonstrate that increasing the prestress load is an effective way to reduce the long-term deflection of RAC beams, and the use of RAC with low RCA replacement ratio is suggested. Besides, the main causes of the long-term deflection and axial shorting of the CFRP prestressed RAC beams are also studied. This research provides a pioneering and insightful study of the long-term behaviour of CFRP prestressed RAC beams. The obtained results demonstrate that the time-dependent effects should be well considered in the design before the prestressed RAC beam is used in practice.",
        "output": "Liu et al. (2023) explored the long-term performance of concrete beams reinforced with CFRP tendons via FE analysis, factoring in concrete creep, shrinkage and tendon relaxation. The model accuracy was confirmed by experimental outcomes, with an error of no more than 5%.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Yao, H.Y.; Hayward, V.; Ellis, R.E. A tactile enhancement instrument for minimally invasive surgery. Comput. Aided Surg. 2005, 10, 233\u2013239.  \nAbstract: Objective: During minimally invasive arthroscopy, surgeons use probes as diagnostic tools to detect tissue anomalies. Improving tactile sensitivity during this activity would be valuable.\nMaterials and Methods: We developed an enhanced probe that could enhance the tactile sensations experienced while probing objects. It operated by detecting the acceleration signal resulting from the interaction of the tool tip with surfaces and by magnifying it for tactile and auditory reproduction. The instrument consisted of an accelerometer and an actuator arranged such that the sensing direction was orthogonal to the actuating direction so as to decouple input from output. Using the instrument, subjects were asked to detect cuts under four conditions: with no amplification, with enhanced tactile feedback, with sound feedback, and with passive touch.\nResults: We found that for tactile reproduction, the current prototype could amplify the signals by 10 dB on average. Results from statistical methods showed significant improvements in performance in the case of tactile and auditory feedbacks.\nConclusion: We developed a surgical probe with tactile and auditory feedbacks. Despite the moderate system gain achievable with the initial prototype, the system could measurably improve users' ability to detect small cuts in cartilage-like elastic surfaces.",
        "output": "Yao et al. (2005) developed a haptic amplification hand-held robot to aid in lesion detection in arthroscopic interventions. A magnetic actuator was used to amplify the signal to provide vibrotactile feedback to the surgeon.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Zhang, C.; Yi, M.; Ye, F.; Xu, Q.; Li, X.; Gan, Q. Application and Evaluation of Deep Neural Networks for Airborne Hyperspectral Remote Sensing Mineral Mapping: A Case Study of the Baiyanghe Uranium Deposit in Northwestern Xinjiang, China. Remote Sens. 2022, 14, 5122. \nAbstract: Deep learning is a popular topic in machine learning and artificial intelligence research and has achieved remarkable results in various fields. In geological remote sensing, mineral mapping is an appealing application of hyperspectral remote sensing for geological surveyors. Whether deep learning can improve the mineral identification ability in hyperspectral remote sensing images, especially for the discrimination of spectrally similar and intimately mixed minerals, needs to be evaluated. In this study, shortwave airborne spectrographic imager (SASI) hyperspectral images of the Baiyanghe uranium deposit in Northwestern Xinjiang, China, were used as experimental data. Three deep neural network (DNN) models were designed: a fully connected neural network (FCNN), a one-dimensional convolutional neural network (1D CNN), and a one-dimensional and two-dimensional convolutional neural network (1D and 2D CNN). A sample dataset containing five minerals was constructed for model training and validation, which was divided into training, validation and test sets at a ratio of 6:2:2. The final test accuracies of the FCNN, 1D CNN, and 1D and 2D CNN were 91.24%, 93.67% and 94.77%, respectively. The three DNNs were used for mineral identification and mapping of SASI hyperspectral images of the Baiyanghe uranium mining area. The mapping results were compared with the mapping results of the support vector machine (SVM) and the mixture-tuned matched filtering (MTMF) method. Combined with the ground spectral data obtained by the spectrometer, spectral verification and interpretation were carried out on sections that the two kinds of methods identified differently. The verification results show that the mapping results of the 1D and 2D CNN were more accurate than those of the other methods. More importantly, for minerals with similar spectral characteristics, such as short-wavelength white mica and medium-wavelength white mica, the 1D and 2D CNN model had a more accurate discrimination effect than the other DNN models, indicating that the introduction of spatial information can improve the mineral identification ability in hyperspectral remote sensing images. In general, CNNs have good application prospects in geological mapping of hyperspectral remote sensing images and are worthy of further development in future work.",
        "output": "Zhang et al. (2022) combined a 1-D CNN with a 2-D CNN, which enhanced the model\u2019s ability to extract rock spectral features and improve the classification accuracy. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Z. Chu, C. Lin, K. Yang, H. Cheng, X. Gu, B. Wang, L. Wu, J. Ma Lability, bioaccessibility, and ecological and health risks of anthropogenic toxic heavy metals in the arid calcareous soil around a nonferrous metal smelting area Chemosphere, 307 (2022), Article 136200 \nAbstract: Lability and bioaccessibility of anthropogenic toxic heavy metals in arid calcareous soils are critical to understand their ecological and health risks. This study examined toxic heavy metal speciation in the calcareous soil contaminated by nonferrous metal smelting. Results demonstrated that approximately 70 years\u2019 nonferrous metal smelting and mining in Baiyin led to significant contamination of nearby soil down to about 200 cm depth by cadmium (Cd), copper (Cu), lead (Pb), and zinc (Zn), with more serious contamination in the downwind areas of smelting or mining. More than half of Cd, Cu, Pb, and Zn in the soil was present in the labile fractions while more than 75% of cobalt (Co), chromium (Cr), nickel (Ni), and vanadium (V) was present in the residual fraction. Carbonate minerals in this calcareous soil play an important role in the labile fractions, with approximate 25% of Cd and Pb and 15% of Cu and Zn bound in carbonates. Bioaccessible Cd, Cu, Pb, and Zn in the soil were approximately 49.8%, 29.4%, 12.2%, and 33.8% in gastric phase and 13.5%, 15.9%, 4.3%, and 9.1% in intestinal phase of their total concentrations, respectively. Therefore, Cd and Zn were removed from gastric solution to a greater extent than Cu and Pb by neutral intestine environment. However, bioaccessible Co, Cr, Ni, and V in the soil were less than 3% of their total concentrations. Bioaccessibility of these metals but Cu in this calcareous soil was significantly lower than that for the acidic Ultisols and Alfisols in U.S. The concentrations of Cd, Cu, Pb, Zn, and Ni in each chemical and bioaccessible forms were significantly correlated linearly with their total concentrations in the calcareous soil, while only residual concentration was significantly correlated with the total concentration for Co, Cr, and V. These linear slopes showed that relative lability and bioaccessibility increased for Cd, but decreased for Cu, Pb, and Zn with the increase in their total concentrations in the calcareous soil. Direct oral soil ingestion would not pose a non-carcinogenic health risk to local children. However, very high potential ecological risk would be caused by these metals in the soil. These results provide improved insights into the biogeochemical processes of anthropogenic toxic heavy metals in the arid calcareous soils worldwide.",
        "output": "Chu et al.(2022) noted that a large amount of heavy metals present in soil are soluble and exchangeable forms, which are available for plants and animal uptake, causing high ecological risks.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Huang, Z.; Pan, Z.; Lei, B. What, where, and how to transfer in SAR target recognition based on deep CNNs. IEEE Trans. Geosci. Remote Sens. 2019, 58, 2324\u20132336. \nAbstract: Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated data set in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in synthetic aperture radar (SAR) image interpretation. Transfer learning provides an effective way to solve this problem by borrowing knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pretrained with a large-scale natural image data set, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR applications because of the prominent discrepancy between SAR and optical images. In this article, we attempt to discuss three issues that are seldom studied before in detail: 1) what network and source tasks are better to transfer to SAR targets; 2) in which layer are transferred features more generic to SAR targets; and 3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multisource data with domain adaptation is proposed in this article to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively.",
        "output": "Huang et al. (2019) explored the application of transfer learning in SAR ship classification. They transferred knowledge learned from the MSTAR and ImageNet datasets to the OpenSARShip dataset for ship classification. Furthermore, they proposed the Deep SAR-Net model to facilitate knowledge transfer from optical to SAR imagery, ultimately improving recognition accuracy for bulk carriers, container ships, and oil tankers.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Gao, Y., Zhang, Y., Ma, C., Zheng, X., Li, T., Zeng, P., et al. (2023a). Failure process and stability analysis of landslides in Southwest China while considering rainfall and supporting conditions. Front. Environ. Sci. 10, 1084151. doi:10.3389/fenvs.2022.1084151 \nAbstract: Landslides frequently occur in several mountainous areas because of their unique engineering-geological conditions and other external factors (earthquakes, rainfall, etc.). In this paper, the landslide in Southwest China is used as the research objective to examine the landslide's stability under different working conditions. The influencing factors and the formation mechanism of the landslide are analyzed based on the geological environment and essential characteristics of the landslide. In addition, the transfer coefficient method and the GeoStudio software were used to assess the landslide stability. The analysis results demonstrate that the joint action of landforms, geological structures, rainfall, and other factors caused the landslide. Furthermore, the slipped tension fracture induced the failure mode. The transfer coefficient method results showed that the landslide was stable under natural conditions and unstable under rainstorm conditions, which is consistent with the numerical simulation result. The shear strength sensitivity analysis results depicted an apparent linear relationship among cohesion c, internal friction angle phi, and stability coefficient. Moreover, the stability of the unstable slope is more sensitive to phi than to c.",
        "output": "Gao et al. (Gao Y. et al., 2023)used the transfer coefficient method to evaluate the landslide stability. The calculated results showed the slope is unstable under rainstorm, which is agree with the numerical simulation results. ",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Jorgenson, A., Clark, R., Kentor, J., and Rieger, A. (2022). Networks, stocks, and climate change: a new approach to the study of foreign investment and the environment. Energy Res. Soc. Sci. 87, 102461. doi:10.1016/j.erss.2021.102461 \nAbstract: This study offers a new approach to the study of foreign direct investment (FDI) and the environment. We argue that both the accumulation of inward FDI and a nation's position in the global network of FDI could facilitate either environmentally beneficial spillover effects and technology transfers or the outsourcing and distancing of environmentally harmful and ecologically unsustainable economic activities. In other words, the environmental impacts, good or bad, are potentially greater for nations that occupy more central positions in the world's FDI network and for nations with relatively larger amounts of inward FDI. To test these arguments, we estimate cross-national longitudinal models of total carbon dioxide emissions and carbon dioxide emissions per unit of GDP. The results suggest that both emissions outcomes are positively associated with inward FDI stocks and FDI network centrality for the overall sample of nations, but these positive associations are much more pronounced for Global South nations than for Global North nations. Overall, the findings are consistent with the arguments that foreign investment facilitates the outsourcing of energy inefficiency and environmentally harmful production processes, leading to growth in fossil-fuel consumption and concomitant carbon emissions for receiving nations, especially in the Global South. We conclude by summarizing the limitations of our analysis, and outline some next steps for this new approach to the study of FDI and the environment.",
        "output": "Studies by Jorgenson et al. (2022) indicate that countries that occupy a central position in the global network of foreign direct investment and those with large inflows of foreign direct investment, regardless of their actual nature, tend to have negative environmental impacts (Jorgenson et al., 2022)",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Guo, Y.; Zhou, L. MEA-Net: A Lightweight SAR Ship Detection Model for Imbalanced Datasets. Remote Sens. 2022, 14, 4438. \nAbstract: The existing synthetic aperture radar (SAR) ship datasets have an imbalanced number of inshore and offshore ship targets, and the number of small, medium and large ship targets differs greatly. At the same time, the existing SAR ship detection models in the application have a huge structure and require high computing resources. To solve these problems, we propose a SAR ship detection model named mask efficient adaptive network (MEA-Net), which is lightweight and high-accuracy for imbalanced datasets. Specifically, we propose the following three innovative modules. Firstly, we propose a mask data balance augmentation (MDBA) method, which solves the imbalance of sample data between inshore and offshore ship targets by combining mathematical morphological processing and ship label data to greatly improve the ability of the model to detect inshore ship targets. Secondly, we propose an efficient attention mechanism (EAM), which effectively integrates channel features and spatial features through one-dimensional convolution and two-dimensional convolution, to improve the feature extraction ability of the model for SAR ship targets. Thirdly, we propose an adaptive receptive field block (ARFB), which can achieve more effective multi-scale detection by establishing the mapping relationship between the size of the convolution kernel and the channel of feature map, to improve the detection ability of the model for ship targets of different sizes. Finally, MEA-Net is deployed on the Jeston Nano edge computing device of the 2 GB version. We conducted experimental validation on the SSDD and HRSID datasets. Compared with the baseline, the AP of MEA-Net increased by 2.18% on the SSDD dataset and 3.64% on the HRSID dataset. The FLOPs and model parameters of MEA-Net were only 2.80 G and 0.96 M, respectively. In addition, the FPS reached 6.31 on the Jeston Nano, which has broad application prospects.",
        "output": "To improve the generalisation ability of the target detection model to SAR maritime ship targets, Guo et al. (2022), proposed an SAR ship detection model called Masked Efficient Adaptive Network (MEA-Net), which is lightweight and highly accurate for unbalanced datasets.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "He, G.H.; Du, Y.B.; Liang, Q.; Zhou, Z.J.; Shu, L.S. Modeling and Optimization Method of Laser Cladding Based on GA-ACO-RFR and GNSGA-II. Int. J. Precis. Eng. Manuf.-Green Technol. 2023, 10, 1207\u20131222. \nAbstract: Laser cladding is an environmentally friendly and reliable surface modification technology. The quality characteristics of the coating are directly affected by the process parameters of laser cladding. The reasonable selection of process parameters is essential to obtain high-quality coating. In this study, the single-track 15-5PH alloy coating was fabricated on the surface of 12Cr13 stainless steel. In view of the hybrid Genetic Algorithm and Ant Colony Optimization (GA-ACO) can effectively improve the prediction ability and robustness of Random Forest Regression (RFR), a prediction method of cladding layer quality characteristics based on GA-ACO-RFR was proposed. The fast non-dominated ranking genetic algorithm with elite strategy by introducing the Gaussian distribution crossover operator (GNSGA-II) was used to optimize the process parameters of laser cladding. The results showed that the multi-objective optimization method of laser cladding process parameters proposed in this paper can obtain high-quality laser cladding coating. This work demonstrated the potential of the proposed method in laser cladding process prediction and optimization.",
        "output": "He et al. (2023) constructed a random forest regression prediction model for process parameters and coating effect. They utilized the GNSGA-II algorithm to achieve the Pareto solution set, leading to the selection of the optimal process parameters.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Deng, M.K.; Ma, F.D.; Ye, W.; Yin, P.F. Experimental study on aseismic behavior of locally used HDC assembled frame beam-column joints. Eng. Mech. 2019, 36, 68\u201378. \nAbstract: In order to improve the deformation and energy dissipation capacity of fabricated beam-column joints and avoid the construction difficulties caused by crowded steel bars, high ductile fiber reinforced concrete (HDC) is used as the core material of beam-column joints. Considering the influence of axial compression ratio and stirrup ratio, 5 fabricated beam-column joints partly adopted HDC and 1 reinforced concrete (RC) beam-column joint were tested. The failure patterns, hysteretic characteristics, deformation capacity, stiffness degradation, energy dissipation capacity and shear deformation of the joint core area were analyzed. The results are as follow. First, failure position changed from node core area to beam end after adopted HDC in node core area. The design principle of a strong node is realized, and the deformation ability and energy dissipation capacity of frame nodes are effectively improved. Second, column ends should be strengthened because the failure position transferred to the end of column adopted HDC in the node area and beam end. Third, the amount of stirrups can be reduced when HDC is used in node core area.",
        "output": "In terms of post-cast material types, Deng et al. (2019) utilized high ductile concrete (HDC) to replace ordinary concrete in beam\u2013column joints, discovering that HDC significantly enhanced both the deformation potential and energy absorption of the frame joints.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Bentes, C.; Velotto, D.; Tings, B. Ship classification in TerraSAR-X images with convolutional neural networks. IEEE J. Ocean. Eng. 2017, 43, 258\u2013266. \nAbstract: Synthetic aperture radar (SAR) is an important instrument for oceanographic observations, providing detailed information of oceans' surface and artificial floating structures. Due to advances in SAR technology and deployment of new SAR satellites, an increasing amount of data is available, and the development of efficient classification systems based on deep learning is possible. A deep neural network has improved the state of the art in classification tasks of optical images, but its use in SAR classification problems has been less exploited. In this paper, a full workflow for SAR maritime targets detection and classification on TerraSAR-X high-resolution image is presented, and convolutional neural networks (CNNs) recently proposed in the literature are cross evaluated on a common data set composed of five maritime classes, namely, cargo, tanker, windmill, platform, and harbor structure. Based on experiments and tests, a multiple input resolution CNN model is proposed and its performance is evaluated. Our results indicate that CNNs are efficient models to perform maritime target classification in SAR images, and the combination of different input resolutions in the CNN model improves its ability to derive features, increasing the overall classification score.",
        "output": "Bentes et al. (2017) proposed a multi-resolution input CNN to enhance multi-scale feature representation. They integrated four distinct CNN classifiers to distinguish between cargo ships, oil tankers, offshore platforms, and port facilities. Their experimental results demonstrated superior recognition accuracy compared to traditional machine learning classifiers like Support Vector Machines (SVMs).",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Lee, J.; Madanat, S.; Reger, D. Pavement systems reconstruction and resurfacing policies for minimization of life-cycle costs under greenhouse gas emissions constraints. Transp. Res. Part B 2016, 93, 618\u2013630. \nAbstract: Pavement management systems, designed to minimize total lifecycle costs, will need to evolve to meet the needs of the future. Environmental concerns are likely to add an additional consideration for the state DOTs when allocating their financial resources. Transportation agencies will be concerned with determining maintenance, resurfacing and reconstruction policies for pavement segments in their systems while also addressing the environmental impact of these activities.\nIn this paper, we propose an efficient solution to solve for pavement resurfacing and reconstruction policies that minimize societal (agency and user) costs under a Greenhouse Gas (GHG) emissions constraint. The main methodological contribution of this work relative to the state of the art is that we formulate the problem to include multi-dimensional pavement segment states and heterogeneous management activities. It allows for a more realistic representation of the majority of current pavements in the world. For example, the assumption that pavements are perpetual, i.e., do not need reconstruction during their lifetime, can be relaxed. A case study using California roads is performed; we find that, for that specific group of pavement segments, the optimal policies to minimize societal costs do not vary greatly from the policies that minimize GHG emissions. An agency can use these results to determine what GHG emission budgets are feasible for the highway system that it manages.",
        "output": "Lee et al. (2016) constructed a multi-dimensional pavement segment status and a heterogeneous management activities model considering greenhouse gas emissions, aiming to minimize life cycle costs for pavement maintenance.",
        "system": "",
        "history": []
    },
    {
        "instruction": "According to the information and abstract data provided, generate a literature review for the paper. ",
        "input": "Liu, X.; Wang, W.; Wang, Z.; Song, J.; Li, K. Simulation Study on Outdoor Wind Environment of Residential Complexes in Hot-Summer and Cold-Winter Climate Zones Based on Entropy-Based TOPSIS Method. Sustainability 2023, 15, 12480. \nAbstract: Driven by a large digital simulation environment, CFD calculation software is used to simulate test results so that they can be effectively applied to engineering practice. This paper explores the suitable outdoor wind environment for residential areas in the hot summer and the cold winter. Taking Xishan Huijing in Changsha as an example, the most unfavorable wind field environment is used as the boundary condition, and the optimal design mode for this residential area is explored based on the Butterfly platform. The research in this paper is mainly divided into five steps: (1) using Rhino 7.0 to establish a 3D model; (2) using the Butterfly 0.0.05 platform to simulate the wind field and export the data at the same time, and to realize the preview through the visualization method; (3) processing the exported simulation data and the calculation of related indices; (4) applying the entropy-based TOPSIS method on the MATLAB 2020 platform to rank the preferred scheme and obtain the corresponding index weights; and (5) using a K-means cluster analysis on SPSS 26 software to optimize the scheme. The results show that (1) the wind environment quality will be overestimated in the summer if the influence of neighboring buildings on the site is not considered, while the opposite is true in the winter, with the error of both reaching two times. (2) The weights of the indicators determined by the TOPSIS entropy weighting method indicate that wind protection in the winter should be prioritized over natural ventilation in the summer in this area. The maximum wind speed in the winter has the most significant weight, reaching 0.287, and the uniformity of the wind field in the summer is the most important, reaching 0.1102. (3) In the layout design of the residential district, the staggered layout of the 60 m high slab houses in the northern, northeastern, and northwestern directions of the site creates a better wind field environment, which attains the highest score by the TOPSIS entropy weighting method, reaching 0.1539, with the second highest score, reaching 0.1511, for the layout method. The research results will provide a scientific basis for the design of residential buildings in the hot-summer and cold-winter regions in China, and also help designers to better grasp the outdoor wind environment of residential buildings in the pre-design stage.",
        "output": "Xiang Liu et al. (2023) employed entropy-based TOPSIS methods combined with CFD simulation techniques to study the wind environment of residential complexes in the hot-summer and cold-winter climate zones. By analyzing the wind environment of a residential area in Changsha under the most unfavorable conditions, they explored optimal design strategies. Their findings highlighted the greater significance of winter wind conditions over summer, particularly regarding building layout.",
        "system": "",
        "history": []
    }
]