This study developed a comprehensive system to evaluate the intensity of cropland use and evolution of cropland use in the Huang-Huai-Hai Plain.Delphi-entropy methods were adopted to determine the weight of the index,...This study developed a comprehensive system to evaluate the intensity of cropland use and evolution of cropland use in the Huang-Huai-Hai Plain.Delphi-entropy methods were adopted to determine the weight of the index,and the Geo Detector model was established to explore the influencing factors.The results are summarized as follows:(1) The intensity of inputs,degree of utilization,and production increased continuously,but the intensity of continuous conditions experienced an overall decline followed by a rebound towards the end of the study period.The number of counties with high and moderately high intensity increased by 56.8% and 14.6%,respectively,from 1996 to 2011.The number of counties with moderately low and low intensity declined by 35.9 % and 11.9 %,respectively.Areas with significant increases in intensity were mainly distributed in northeast Hebei Province,northwest Shandong Province,and north Jiangsu Province.The intensity is high in northern Jiangsu and Anhui;the output effect remained above moderate intensity mainly near Beijing,Tianjin,Tangshan,and counties in the suburbs of Shijiazhuang.(2) Natural disasters,elevation,slope,and road networks were the main factors influencing the intensity of cropland use in this region,with influence values of 0.158,0.143,0.129,and 0.054,respectively.Areas with moderately high and high levels of intensity were distributed in low-lying areas.Uneven distribution of precipitation,seasonal drought,and flood disasters can directly affect the stability index of croplands and reduce the intensity of cropland use.Developed road networks are associated with moderately high intensity.Our results suggest recommendations such as promoting agricultural intensification and large-scale management,promoting the construction of road networks,improving early warning systems for drought and flood disasters,and promoting moderate and intensive use of arable land,and focusing on restoration and sustainable use of cropland.展开更多
The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster predic...The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.展开更多
Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual inte...Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.展开更多
Automated guided vehicles(AGVs)are key equipment in automated container terminals(ACTs),and their operational efficiency can be impacted by conflicts and battery swapping.Additionally,AGVs have bidirectional transport...Automated guided vehicles(AGVs)are key equipment in automated container terminals(ACTs),and their operational efficiency can be impacted by conflicts and battery swapping.Additionally,AGVs have bidirectional transportation capabilities,allowing them tomove in the opposite directionwithout turning around,which helps reduce transportation time.This paper aims at the problem of AGV scheduling and bidirectional conflict-free routing with battery swapping in automated terminals.A bi-level mixed integer programming(MIP)model is proposed,taking into account task assignment,bidirectional conflict-free routing,and battery swapping.The upper model focuses on container task assignment and AGV battery swapping planning,while the lower model ensures conflict-free movement of AGVs.A double-threshold battery swapping strategy is introduced,allowing AGVs to utilize waiting time for loading for battery swapping.An improved differential evolution variable neighborhood search(IDE-VNS)algorithm is developed to solve the bi-level MIP model,aiming to minimize the completion time of all jobs.Experimental results demonstrate that compared to the differential evolution(DE)algorithm and the genetic algorithm(GA),the IDEVNS algorithmreduces fitness values by 44.49% and 45.22%,though it does increase computation time by 56.28% and 62.03%,respectively.Bidirectional transportation reduces the fitness value by an average of 10.97% when the container scale is small.As the container scale increases,the fitness value of bidirectional transportation gradually approaches that of unidirectional transportation.The results further show that the double-threshold battery swapping strategy enhances AGV utilization and reduces the fitness value.展开更多
The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satell...The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satellite observations, the spatio-temporal characteristics of MILS_BRF data have rarely been explicitly and comprehensively analysed. Results from 5-yr(2011–2015) of MILS_BRF dataset from a typical region in central Northeast Asia as the study area showed that the monthly area coverage as well as MILS_BRF data quantity varies significantly, from the highest in October(99.05%) through median in June/July(78.09%/75.21%) to lowest in January(18.97%), and a large data-vacant area exists in the study area during four consecutive winter months(December through March). The data-vacant area is mainly composed of crop lands and cropland/natural vegetation mosaic. The amount of data within the principal plane(PP)±30°(nPP) or cross PP ±30°(nCP), varies intra-annually with significant differences from different view zeniths or forward/backward scattering directions. For example, multiple off-nadir cameras have nPP but no nCP data for up to six months(September through February), with the opposite occurring in June and July. This study provides explicit and comprehensive information about the spatio-temporal characteristics of product coverage and observation geometry of MILS_BRF in the study area. Results provide required user reference information for MILS_BRF to evaluate performance of BRDF models or to compare with other satellite-derived BRF or albedo products. Comparing this final product to on-satellite observations, what was found here reveals a new perspective on product spatial coverage and observation geometry for multi-angle remote sensing.展开更多
The radiative properties of three different materials surfaces with one-dimensional microscale random roughness were obtained with the finite difference time domain method(FDTD) and near-to-far-field transformation.Th...The radiative properties of three different materials surfaces with one-dimensional microscale random roughness were obtained with the finite difference time domain method(FDTD) and near-to-far-field transformation.The surface height conforms to the Gaussian probability density function distribution.Various computational modeling issues that affect the accuracy of the predicted properties were discussed.The results show that,for perfect electric conductor(PEC) surfaces,as the surface roughness increases,the magnitude of the spike reduces and eventually the spike disappears,and also as the ratio of root mean square roughness to the surface correlation distance increases,the retroreflection becomes evident.The predicted values of FDTD solutions are in good agreement with the ray tracing and integral equation solutions.The overall trend of bidirectional reflection distribution function(BRDF) of PEC surfaces and silicon surfaces is the same,but the silicon's is much less than the former's.The BRDF difference from two polarization modes for the gold surfaces is little for smaller wavelength,but it is much larger for the longer wavelength and the FDTD simulation results agree well with the measured data.In terms of PEC surfaces,as the incident angle increases,the reflectivity becomes more specular.展开更多
针对传统基于到达时间差(Time Difference of Arrival,TDOA)定位方法存在的数值结果不确定性导致的定位误差问题,提出了一种采用双向收缩优化的TDOA区间定位算法。该算法在区间前向收缩阶段利用坐标系旋转解决了基站布型导致的定位失败...针对传统基于到达时间差(Time Difference of Arrival,TDOA)定位方法存在的数值结果不确定性导致的定位误差问题,提出了一种采用双向收缩优化的TDOA区间定位算法。该算法在区间前向收缩阶段利用坐标系旋转解决了基站布型导致的定位失败问题,并巧妙地将时差测量转换为双曲线区间,利用二分法将双曲线区间离散成矩形集,并进行区间交叠运算缩小初始定位区间;在区间后向收缩阶段,利用初始定位区间反向收缩双曲线区间。由该算法最终可以得到收敛的区间定位结果。仿真结果表明,优化后的算法在不影响定位精度并且达到了克拉美罗下界的同时,定位结果的面积由40.10 m^(2)缩小到22.20 m^(2),降低了44.6%,置信度始终保持在99.3%以上。展开更多
备件需求预测作为企业精益化管理和提升经济效益的重要手段之一。针对传统预测模型数据利用不充分、精度较低等问题,论文提出了一种新的方法对备件需求进行预测。首先通过最大均值差异(MMD)方法,筛选可迁移的源域数据,降低因多个相似源...备件需求预测作为企业精益化管理和提升经济效益的重要手段之一。针对传统预测模型数据利用不充分、精度较低等问题,论文提出了一种新的方法对备件需求进行预测。首先通过最大均值差异(MMD)方法,筛选可迁移的源域数据,降低因多个相似源域迁移引起信息冗余的可能性。然后将注意力机制(Attention)和双向有序长短时记忆网络(BI ON-LSTM)融合,构造Attention BI ON-LSTM预测模型,通过Attention BI ON-LSTM模型实现对过去和未来信息的充分应用,以及计算不同特征向量的权重,防止包含重要信息的特征消失;最后,通过张量迁移,提取源域训练的张量初始化目标域模型,微调后得到目标域预测结果。实验结果证明,论文提出的方法优于常见的时间序列预测模型。展开更多
Objective:Mendelian randomization(MR)has been widely utilized for causal inference between diseases,and its implementation within the domain of traditional Chinese medicine(TCM)is considered feasible.Although previous...Objective:Mendelian randomization(MR)has been widely utilized for causal inference between diseases,and its implementation within the domain of traditional Chinese medicine(TCM)is considered feasible.Although previous clinical and epidemiological studies have demonstrated a close relationship between insomnia and depression,the inherent genetic factors underlying these associations are unclear.The aim of this study was to evaluate the causal relationship between depression and insomnia via bidirectional 2-sample MR and increase the understanding of the TCM theory of treating different diseases with the same method,particularly in the context of comorbid depression and insomnia.Methods:Genetic data related to depression and insomnia were extracted from published genome-wide association studies(GWAS)data sets.Single-nucleotide polymorphisms(SNPs)associated with depression and insomnia were used as instrumental variables to construct an“SNP-exposure-outcome”model.Bidirectional 2-sample MR analysis was conducted via inverse-variance weighted(IVW),weighted median,MR Egger regression,simple mode,and weighted mode methods.Furthermore,heterogeneity tests,pleiotropy analyses,and sensitivity analyses were performed.Results:The MR results revealed a causal relationship between depression and an increased risk of developing insomnia(IVW,OR=1.400,95%CI:1.246–1.573,P<0.001),and a causal relationship between insomnia and an increased risk of developing depression(IVW,OR=1.204,95%CI:1.144–1.266,P<0.001).Conclusions:There is a bidirectional causal relationship between depression and insomnia.These findings provide new theoretical support for the TCM approach of treating different diseases with the same method in the prevention and treatment of depression and insomnia and provide a scientific basis for the modernization of TCM.展开更多
基金Project of Ministry of Education Humanities and Social Sciences,No.16YJCZH082,No.16YJC630149
文摘This study developed a comprehensive system to evaluate the intensity of cropland use and evolution of cropland use in the Huang-Huai-Hai Plain.Delphi-entropy methods were adopted to determine the weight of the index,and the Geo Detector model was established to explore the influencing factors.The results are summarized as follows:(1) The intensity of inputs,degree of utilization,and production increased continuously,but the intensity of continuous conditions experienced an overall decline followed by a rebound towards the end of the study period.The number of counties with high and moderately high intensity increased by 56.8% and 14.6%,respectively,from 1996 to 2011.The number of counties with moderately low and low intensity declined by 35.9 % and 11.9 %,respectively.Areas with significant increases in intensity were mainly distributed in northeast Hebei Province,northwest Shandong Province,and north Jiangsu Province.The intensity is high in northern Jiangsu and Anhui;the output effect remained above moderate intensity mainly near Beijing,Tianjin,Tangshan,and counties in the suburbs of Shijiazhuang.(2) Natural disasters,elevation,slope,and road networks were the main factors influencing the intensity of cropland use in this region,with influence values of 0.158,0.143,0.129,and 0.054,respectively.Areas with moderately high and high levels of intensity were distributed in low-lying areas.Uneven distribution of precipitation,seasonal drought,and flood disasters can directly affect the stability index of croplands and reduce the intensity of cropland use.Developed road networks are associated with moderately high intensity.Our results suggest recommendations such as promoting agricultural intensification and large-scale management,promoting the construction of road networks,improving early warning systems for drought and flood disasters,and promoting moderate and intensive use of arable land,and focusing on restoration and sustainable use of cropland.
基金supported by the National Research and Development Program(2022YFC3004603)the Jiangsu Province International Collaboration Program-Key National Industrial Technology Research and Development Cooperation Projects(BZ2023050)+1 种基金the Natural Science Foundation of Jiangsu Province(BK20221109)the National Natural Science Foundation of China(52274098).
文摘The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.
基金funded by the National Natural Science Foundation of China,grant number 624010funded by the Natural Science Foundation of Anhui Province,grant number 2408085QF202+1 种基金funded by the Anhui Future Technology Research Institute Industry Guidance Fund Project,grant number 2023cyyd04funded by the Project of Research of Anhui Polytechnic University,grant number Xjky2022150.
文摘Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.
基金supported by National Natural Science Foundation of China(No.62073212)Shanghai Science and Technology Commission(No.23ZR1426600).
文摘Automated guided vehicles(AGVs)are key equipment in automated container terminals(ACTs),and their operational efficiency can be impacted by conflicts and battery swapping.Additionally,AGVs have bidirectional transportation capabilities,allowing them tomove in the opposite directionwithout turning around,which helps reduce transportation time.This paper aims at the problem of AGV scheduling and bidirectional conflict-free routing with battery swapping in automated terminals.A bi-level mixed integer programming(MIP)model is proposed,taking into account task assignment,bidirectional conflict-free routing,and battery swapping.The upper model focuses on container task assignment and AGV battery swapping planning,while the lower model ensures conflict-free movement of AGVs.A double-threshold battery swapping strategy is introduced,allowing AGVs to utilize waiting time for loading for battery swapping.An improved differential evolution variable neighborhood search(IDE-VNS)algorithm is developed to solve the bi-level MIP model,aiming to minimize the completion time of all jobs.Experimental results demonstrate that compared to the differential evolution(DE)algorithm and the genetic algorithm(GA),the IDEVNS algorithmreduces fitness values by 44.49% and 45.22%,though it does increase computation time by 56.28% and 62.03%,respectively.Bidirectional transportation reduces the fitness value by an average of 10.97% when the container scale is small.As the container scale increases,the fitness value of bidirectional transportation gradually approaches that of unidirectional transportation.The results further show that the double-threshold battery swapping strategy enhances AGV utilization and reduces the fitness value.
基金Under the auspices the Fundamental Research Funds for the Central Universities,China(No.2017TD-26)the Plan for Changbai Mountain Scholars of Jilin Province,China(No.JJLZ[2015]54)
文摘The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satellite observations, the spatio-temporal characteristics of MILS_BRF data have rarely been explicitly and comprehensively analysed. Results from 5-yr(2011–2015) of MILS_BRF dataset from a typical region in central Northeast Asia as the study area showed that the monthly area coverage as well as MILS_BRF data quantity varies significantly, from the highest in October(99.05%) through median in June/July(78.09%/75.21%) to lowest in January(18.97%), and a large data-vacant area exists in the study area during four consecutive winter months(December through March). The data-vacant area is mainly composed of crop lands and cropland/natural vegetation mosaic. The amount of data within the principal plane(PP)±30°(nPP) or cross PP ±30°(nCP), varies intra-annually with significant differences from different view zeniths or forward/backward scattering directions. For example, multiple off-nadir cameras have nPP but no nCP data for up to six months(September through February), with the opposite occurring in June and July. This study provides explicit and comprehensive information about the spatio-temporal characteristics of product coverage and observation geometry of MILS_BRF in the study area. Results provide required user reference information for MILS_BRF to evaluate performance of BRDF models or to compare with other satellite-derived BRF or albedo products. Comparing this final product to on-satellite observations, what was found here reveals a new perspective on product spatial coverage and observation geometry for multi-angle remote sensing.
基金Project(2009AA05Z215) supported by the National High-Tech Research and Development Program of China
文摘The radiative properties of three different materials surfaces with one-dimensional microscale random roughness were obtained with the finite difference time domain method(FDTD) and near-to-far-field transformation.The surface height conforms to the Gaussian probability density function distribution.Various computational modeling issues that affect the accuracy of the predicted properties were discussed.The results show that,for perfect electric conductor(PEC) surfaces,as the surface roughness increases,the magnitude of the spike reduces and eventually the spike disappears,and also as the ratio of root mean square roughness to the surface correlation distance increases,the retroreflection becomes evident.The predicted values of FDTD solutions are in good agreement with the ray tracing and integral equation solutions.The overall trend of bidirectional reflection distribution function(BRDF) of PEC surfaces and silicon surfaces is the same,but the silicon's is much less than the former's.The BRDF difference from two polarization modes for the gold surfaces is little for smaller wavelength,but it is much larger for the longer wavelength and the FDTD simulation results agree well with the measured data.In terms of PEC surfaces,as the incident angle increases,the reflectivity becomes more specular.
文摘备件需求预测作为企业精益化管理和提升经济效益的重要手段之一。针对传统预测模型数据利用不充分、精度较低等问题,论文提出了一种新的方法对备件需求进行预测。首先通过最大均值差异(MMD)方法,筛选可迁移的源域数据,降低因多个相似源域迁移引起信息冗余的可能性。然后将注意力机制(Attention)和双向有序长短时记忆网络(BI ON-LSTM)融合,构造Attention BI ON-LSTM预测模型,通过Attention BI ON-LSTM模型实现对过去和未来信息的充分应用,以及计算不同特征向量的权重,防止包含重要信息的特征消失;最后,通过张量迁移,提取源域训练的张量初始化目标域模型,微调后得到目标域预测结果。实验结果证明,论文提出的方法优于常见的时间序列预测模型。
基金supported by the China Academy of ChineseMedical Science(CACMS)Innovation Fund(No.CI2021A00603)the National Natural Science Foundation of China(No.82074299).
文摘Objective:Mendelian randomization(MR)has been widely utilized for causal inference between diseases,and its implementation within the domain of traditional Chinese medicine(TCM)is considered feasible.Although previous clinical and epidemiological studies have demonstrated a close relationship between insomnia and depression,the inherent genetic factors underlying these associations are unclear.The aim of this study was to evaluate the causal relationship between depression and insomnia via bidirectional 2-sample MR and increase the understanding of the TCM theory of treating different diseases with the same method,particularly in the context of comorbid depression and insomnia.Methods:Genetic data related to depression and insomnia were extracted from published genome-wide association studies(GWAS)data sets.Single-nucleotide polymorphisms(SNPs)associated with depression and insomnia were used as instrumental variables to construct an“SNP-exposure-outcome”model.Bidirectional 2-sample MR analysis was conducted via inverse-variance weighted(IVW),weighted median,MR Egger regression,simple mode,and weighted mode methods.Furthermore,heterogeneity tests,pleiotropy analyses,and sensitivity analyses were performed.Results:The MR results revealed a causal relationship between depression and an increased risk of developing insomnia(IVW,OR=1.400,95%CI:1.246–1.573,P<0.001),and a causal relationship between insomnia and an increased risk of developing depression(IVW,OR=1.204,95%CI:1.144–1.266,P<0.001).Conclusions:There is a bidirectional causal relationship between depression and insomnia.These findings provide new theoretical support for the TCM approach of treating different diseases with the same method in the prevention and treatment of depression and insomnia and provide a scientific basis for the modernization of TCM.
