This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically def...This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning mode...Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.展开更多
Traffic flow prediction is an important part of the intelligent transportation system. Accurate multi-step traffic flow prediction plays an important role in improving the operational efficiency of the traffic network...Traffic flow prediction is an important part of the intelligent transportation system. Accurate multi-step traffic flow prediction plays an important role in improving the operational efficiency of the traffic network. Since traffic flow data has complex spatio-temporal correlation and non-linearity, existing prediction methods are mainly accomplished through a combination of a Graph Convolutional Network (GCN) and a recurrent neural network. The combination strategy has an excellent performance in traffic prediction tasks. However, multi-step prediction error accumulates with the predicted step size. Some scholars use multiple sampling sequences to achieve more accurate prediction results. But it requires high hardware conditions and multiplied training time. Considering the spatiotemporal correlation of traffic flow and influence of external factors, we propose an Attention Based Spatio-Temporal Graph Convolutional Network considering External Factors (ABSTGCN-EF) for multi-step traffic flow prediction. This model models the traffic flow as diffusion on a digraph and extracts the spatial characteristics of traffic flow through GCN. We add meaningful time-slots attention to the encoder-decoder to form an Attention Encoder Network (AEN) to handle temporal correlation. The attention vector is used as a competitive choice to draw the correlation between predicted states and historical states. We considered the impact of three external factors (daytime, weekdays, and traffic accident markers) on the traffic flow prediction tasks. Experiments on two public data sets show that it makes sense to consider external factors. The prediction performance of our ABSTGCN-EF model achieves 7.2%–8.7% higher than the state-of-the-art baselines.展开更多
In the process of logistics distribution of manufacturing enterprises, the automatic scheduling method based on the algorithm model has the advantages of accurate calculation and stable operation, but it excessively r...In the process of logistics distribution of manufacturing enterprises, the automatic scheduling method based on the algorithm model has the advantages of accurate calculation and stable operation, but it excessively relies on the results of data calculation, ignores historical information and empirical data in the solving process, and has the bottleneck of low processing dimension and small processing scale. Therefore, in the digital twin(DT) system based on virtual and real fusion, a modeling and analysis method of production logistics spatio-temporal graph network model is proposed, considering the characteristics of road network topology and time-varying data. In the DT system, the temporal graph network model of the production logistics task is established and combined with the network topology, and the historical scheduling information about logistics elements is stored in the nodes. When the dynamic task arrives, a multi-stage links probability prediction method is adopted to predict the possibility of loading, driving, and other link relationships between task-related entity nodes at each stage. Several experiments are carried out, and the prediction accuracy of the digital twin-based temporal graph network(DTGN) model trained by historical scheduling information reaches 99.2% when the appropriate batch size is selected. Through logistics simulation experiments, the feasibility and the effectiveness of production logistics spatio-temporal graph network analysis methods based on historical scheduling information are verified.展开更多
Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficie...Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficiency of roadway infrastructure.However,existingmethods struggle in complex traffic scenarios due to static spatio-temporal embedding,restricted multi-scale temporal modeling,and weak representation of local spatial interactions.This study proposes Bi-STAT+,an enhanced bidirectional spatio-temporal attention framework to address existing limitations through three principal contributions:(1)an adaptive spatio-temporal embedding module that dynamically adjusts embeddings to capture complex traffic variations;(2)frequency-domain analysis in the temporal dimension for simultaneous high-frequency details and low-frequency trend extraction;and(3)an agent attention mechanism in the spatial dimension that enhances local feature extraction through dynamic weight allocation.Extensive experiments were performed on four distinct datasets,including two publicly benchmark datasets(PEMS04 and PEMS08)and two private datasets collected from Baotou and Chengdu,China.The results demonstrate that Bi-STAT+consistently outperforms existing methods in terms of MAE,RMSE,and MAPE,while maintaining strong robustness against missing data and noise.Furthermore,the results highlight that prediction accuracy improves significantly with higher sampling rates,providing crucial insights for optimizing real-world deployment scenarios.展开更多
The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast ...The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast charge leads to the lithium concentration gradient in the solid and electrolyte phases and the non-uniform electrochemical reaction at the solid/electrolyte interface.In order to decouple charge transfer reactions in LIBs under dynamic conditions,understanding the spatio-temporal resolution of the P2D model is urgently required.Till now,the study of this aspect is still insufficient.This work studies the spatio-temporal resolution for dynamic/static electrochemical impedance spectroscopy(DEIS/SEIS)on multiple scales.In detail,DEIS and SEIS with spatio-temporal resolutions are used to decouple charge transfer reactions in LIBs based on the numerical solution of the P2D model in the frequency domain.The calculated results indicate that decoupling solid diffusion requires a high spatial resolution along the r-direction in particles,decoupling electrolyte diffusion and interfacial transfer reaction requires a high spatial resolution along the x-direction,and decoupling charge transfer reactions in LIBs at an extremely low state of charge(SOC)requires an extremely high temporal resolution along the t-direction.Finally,the optimal range of spatio-temporal resolutions for DEIS/SEIS is derived,and the method to decouple charge transfer reactions with spatio-temporal resolutions is developed.展开更多
As one of the most crucial topics in the recommendation system field,point-of-interest(POI)recommendation aims to recommending potential interesting POIs to users.Recently,graph neural networks(GNNs)have been successf...As one of the most crucial topics in the recommendation system field,point-of-interest(POI)recommendation aims to recommending potential interesting POIs to users.Recently,graph neural networks(GNNs)have been successfully used to model interaction and spatio-temporal information in POI recommendations,but the data sparsity of POI recommendations affects the training of GNNs.Although some existing GNN-based POI recommendation approaches try to use social relationships or user attributes to alleviate the data sparsity problem,such auxiliary information is not always available for privacy reasons.Self-supervised learning gives a new idea to alleviate the data sparsity problem,but most existing self-supervised recommendation methods cannot be directly used in the spatio-temporal graph of POI recommendations.In this paper,we propose a novel heterogeneous spatio-temporal graph contrastive learning method,HestGCL,to compensate for existing GNN-based methods’shortcomings.To model spatio-temporal information,we generate spatio-temporally specific views and design view-specific heterogeneous graph neural networks to model spatial and temporal information,respectively.To alleviate data sparsity,we propose a cross-view contrastive strategy to capture differences and correlations among views,providing more supervision signals and boosting the overall performance collaboratively.Extensive experiments on three benchmark datasets demonstrate the effectiveness of HestGCL,which significantly outperforms existing methods.展开更多
Long-term traffic flow prediction is a crucial component of intelligent transportation systems within intelligent networks,requiring predictive models that balance accuracy with low-latency and lightweight computation...Long-term traffic flow prediction is a crucial component of intelligent transportation systems within intelligent networks,requiring predictive models that balance accuracy with low-latency and lightweight computation to optimize trafficmanagement and enhance urban mobility and sustainability.However,traditional predictivemodels struggle to capture long-term temporal dependencies and are computationally intensive,limiting their practicality in real-time.Moreover,many approaches overlook the periodic characteristics inherent in traffic data,further impacting performance.To address these challenges,we introduce ST-MambaGCN,a State-Space-Based Spatio-Temporal Graph Convolution Network.Unlike conventionalmodels,ST-MambaGCN replaces the temporal attention layer withMamba,a state-space model that efficiently captures long-term dependencies with near-linear computational complexity.The model combines Chebyshev polynomial-based graph convolutional networks(GCN)to explore spatial correlations.Additionally,we incorporate a multi-temporal feature capture mechanism,where the final integrated features are generated through the Hadamard product based on learnable parameters.This mechanism explicitly models shortterm,daily,and weekly traffic patterns to enhance the network’s awareness of traffic periodicity.Extensive experiments on the PeMS04 and PeMS08 datasets demonstrate that ST-MambaGCN significantly outperforms existing benchmarks,offering substantial improvements in both prediction accuracy and computational efficiency for long-term traffic flow prediction.展开更多
Digital manufacturing enterprises require high operational agility due to the intricate and dynamically changing nature of their tasks.The implementation of accurate and timely predictions of task bottlenecks is there...Digital manufacturing enterprises require high operational agility due to the intricate and dynamically changing nature of their tasks.The implementation of accurate and timely predictions of task bottlenecks is therefore crucial to enhancing overall efficiency.Due to task complexities and dynamic business environments,bottleneck prediction is a challenging issue.This study introduces a novel approach that constructs a task network from extensive data accumulated within a digital enterprise to identify and depict the complex interrelations among tasks.Based on this method,we develop a Bottleneck Spatio-Temporal Graph Convolutional Network (BTGCN) model based on deep learning methods that considers spatial features of the task network and temporal data of task execution and integrates the strengths of GCN and GRU.We find that GCN effectively learns and represents the complex topology of task networks to capture spatial dependencies,while GRU adapts to the dynamic changes in task data,accurately capturing temporal dependencies.Informed by the theory of constraints,the study applies the proposed BTGCN model to the prediction of task throughput bottlenecks in digital enterprises.Experimental results demonstrate that while the model has certain limitations,it can accurately extract spatio-temporal correlations from system data,offering advantages in bottleneck prediction over other benchmark models.展开更多
Using skeletal information to model and recognize human actions is currently a hot research subject in the realm of Human Action Recognition(HAR).Graph Convolutional Networks(GCN)have gained popularity in this discipl...Using skeletal information to model and recognize human actions is currently a hot research subject in the realm of Human Action Recognition(HAR).Graph Convolutional Networks(GCN)have gained popularity in this discipline due to their capacity to efficiently process graph-structured data.However,it is challenging for current models to handle distant dependencies that commonly exist between human skeleton nodes,which hinders the development of algorithms in related fields.To solve these problems,the Lightweight Multiscale Spatio-Temporal Graph Convolutional Network(LMSTGCN)is proposed.Firstly,the Lightweight Multiscale Spatial Graph Convolutional Network(LMSGCN)is constructed to capture the information in various hierarchies,and multiple inner connections between skeleton joints are captured by dividing the input features into a number of subsets along the channel direction.Secondly,the dilated convolution is incorporated into the temporal convolution to construct Lightweight Multiscale Temporal Convolutional Network(LMTCN),which allows to obtain a wider receptive field while keeping the size of the convolution kernel unchanged.Thirdly,the Spatio-Temporal Location Attention(STLAtt)module is used to identify the most informative joints in the sequence of skeletal information at a specific frame,hence improving the model’s ability to extract features and recognize actions.Finally,multi-stream data fusion input structure is used to enhance the input data and expand the feature information.Experiments on three public datasets illustrate the effectiveness of the proposed network.展开更多
Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LM...Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LMRB's terrestrial water storage anomaly(TWSA)and its spatio-temporal dynamics during 2002–2020.Considering the effects of natural factors and human activities,the respective contributions of climate variability and human activities to terrestrial water storage change(TWSC)were separated.Results showed that:(1)LMRB's TWSA decreased by 0.3158 cm/a.(2)TWSA showed a gradual increase in distribution from southwest of MRB to middle LMRB and from northeast of LRB to middle LMRB.TWSA positively changed in Myanmar while slightly changed in Laos and China.It negatively changed in Vietnam,Thailand and Cambodia.(3)TWSA components decreased in a descending order of soil moisture,groundwater and precipitation.(4)Natural factors had a substantial and spatial differentiated influence on TWSA over the LMRB.(5)Climate variability contributed 79%of TWSC in the LMRB while human activities contributed 21%with an increasing impact after 2008.The TWSC of upstream basin countries was found to be controlled by climate variability while Vietnam and Cambodia's TWSC has been controlled by human activities since 2012.展开更多
In recent years, the large scale and frequency of severe air pollution in China has become an important consideration in the construction of livable cities and the physical and mental health of urban residents. Based ...In recent years, the large scale and frequency of severe air pollution in China has become an important consideration in the construction of livable cities and the physical and mental health of urban residents. Based on the 2016-year urban air quality index(AQI) data published by the Ministry of Environmental Protection of China, this study analyzed the spatial and temporal characteristics of air quality and its influencing factors in 338 urban units nationwide. The analysis provides an effective scientific basis for formulating national air pollution control measures. Four key results are shown. 1) Generally, air quality in the 338 cities is poor, and the average annual values for urban AQI and air pollution in 2016 were 79.58% and 21.22%, respectively. 2) The air quality index presents seasonal changes, with winter > spring > autumn > summer and a u-shaped trend. 3) The spatial distribution of the urban air quality index shows clear north-south characteristic differences and a spatial agglomeration effect; the high value area of air pollution is mainly concentrated in the North China Plain and Xinjiang Uygur Autonomous Region. 4) An evaluation of the spatial econometric model shows that differences in urban air quality are due to social, economic, and natural factors.展开更多
Exploring the spatio-temporal dynamics of poverty is important for research on sustainable poverty reduction in China. Based on the perspective of development geography, this paper proposes a panel vector autoregressi...Exploring the spatio-temporal dynamics of poverty is important for research on sustainable poverty reduction in China. Based on the perspective of development geography, this paper proposes a panel vector autoregressive(PVAR) model that combines the human development approach with the global indicator framework for Sustainable Development Goals(SDGs) to identify the poverty-causing and the poverty-reducing factors in China. The aim is to measure the multidimensional poverty index(MPI) of China’s provinces from 2007 to 2017, and use the exploratory spatio-temporal data analysis(ESTDA) method to reveal the characteristics of the spatio-temporal dynamics of multidimensional poverty. The results show the following:(1) The poverty-causing factors in China include the high social gross dependency ratio and crop-to-disaster ratio, and the poverty-reducing factors include the high per capita GDP, per capita social security expenditure, per capita public health expenditure, number of hospitals per 10,000 people, rate of participation in the new rural cooperative medical scheme, vegetation coverage, per capita education expenditure, number of universities, per capita research and development(R&D) expenditure, and funding per capita for cultural undertakings.(2) From 2007 to 2017, provincial income poverty(IP), health poverty(HP), cultural poverty(CP), and multidimensional poverty have been significantly reduced in China, and the overall national poverty has dropped by 5.67% annually. there is a differentiation in poverty along different dimensions in certain provinces.(3) During the study period, the local spatial pattern of multidimensional poverty between provinces showed strong spatial dynamics, and a trend of increase from the eastern to the central and western regions was noted. The MPI among provinces exhibited a strong spatial dependence over time to form a pattern of decrease from northwestern and northeastern China to the surrounding areas.(4) The spatio-temporal networks of multidimensional poverty in adjacent provinces were mainly negatively correlated, with only Shaanxi and Henan, Shaanxi and Ningxia, Qinghai and Gansu, Hubei and Anhui, Sichuan and Guizhou, and Hainan and Guangdong forming spatially strong cooperative poverty reduction relationships. These results have important reference value for the implementation of China’s poverty alleviation strategy.展开更多
Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoenc...Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.展开更多
Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges...Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.展开更多
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2023-00249743).
文摘This study proposes a novel forecasting framework that simultaneously captures the strong periodicity and irregular meteorological fluctuations inherent in solar radiation time series.Existing approaches typically define inter-regional correlations using either simple correlation coefficients or distance-based measures when applying spatio-temporal graph neural networks(STGNNs).However,such definitions are prone to generating spurious correlations due to the dominance of periodic structures.To address this limitation,we adopt the Elastic-Band Transform(EBT)to decompose solar radiation into periodic and amplitude-modulated components,which are then modeled independently with separate graph neural networks.The periodic component,characterized by strong nationwide correlations,is learned with a relatively simple architecture,whereas the amplitude-modulated component is modeled with more complex STGNNs that capture climatological similarities between regions.The predictions from the two components are subsequently recombined to yield final forecasts that integrate both periodic patterns and aperiodic variability.The proposed framework is validated with multiple STGNN architectures,and experimental results demonstrate improved predictive accuracy and interpretability compared to conventional methods.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金Youth Innovation Promotion Association CAS,Grant/Award Number:2021103Strategic Priority Research Program of Chinese Academy of Sciences,Grant/Award Number:XDC02060500。
文摘Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.
基金supported by the Nation Natural Science Foundation of China(NSFC)under Grant No.61462042 and No.61966018.
文摘Traffic flow prediction is an important part of the intelligent transportation system. Accurate multi-step traffic flow prediction plays an important role in improving the operational efficiency of the traffic network. Since traffic flow data has complex spatio-temporal correlation and non-linearity, existing prediction methods are mainly accomplished through a combination of a Graph Convolutional Network (GCN) and a recurrent neural network. The combination strategy has an excellent performance in traffic prediction tasks. However, multi-step prediction error accumulates with the predicted step size. Some scholars use multiple sampling sequences to achieve more accurate prediction results. But it requires high hardware conditions and multiplied training time. Considering the spatiotemporal correlation of traffic flow and influence of external factors, we propose an Attention Based Spatio-Temporal Graph Convolutional Network considering External Factors (ABSTGCN-EF) for multi-step traffic flow prediction. This model models the traffic flow as diffusion on a digraph and extracts the spatial characteristics of traffic flow through GCN. We add meaningful time-slots attention to the encoder-decoder to form an Attention Encoder Network (AEN) to handle temporal correlation. The attention vector is used as a competitive choice to draw the correlation between predicted states and historical states. We considered the impact of three external factors (daytime, weekdays, and traffic accident markers) on the traffic flow prediction tasks. Experiments on two public data sets show that it makes sense to consider external factors. The prediction performance of our ABSTGCN-EF model achieves 7.2%–8.7% higher than the state-of-the-art baselines.
基金National Key Research and Development Plan of China (No.2019YFB1706300)Shanghai Frontier Science Research Center for Modern Textiles (Donghua University),China。
文摘In the process of logistics distribution of manufacturing enterprises, the automatic scheduling method based on the algorithm model has the advantages of accurate calculation and stable operation, but it excessively relies on the results of data calculation, ignores historical information and empirical data in the solving process, and has the bottleneck of low processing dimension and small processing scale. Therefore, in the digital twin(DT) system based on virtual and real fusion, a modeling and analysis method of production logistics spatio-temporal graph network model is proposed, considering the characteristics of road network topology and time-varying data. In the DT system, the temporal graph network model of the production logistics task is established and combined with the network topology, and the historical scheduling information about logistics elements is stored in the nodes. When the dynamic task arrives, a multi-stage links probability prediction method is adopted to predict the possibility of loading, driving, and other link relationships between task-related entity nodes at each stage. Several experiments are carried out, and the prediction accuracy of the digital twin-based temporal graph network(DTGN) model trained by historical scheduling information reaches 99.2% when the appropriate batch size is selected. Through logistics simulation experiments, the feasibility and the effectiveness of production logistics spatio-temporal graph network analysis methods based on historical scheduling information are verified.
基金partly supported by the Youth Foundation of the Inner Mongolia Natural Science Foundation[grant number 2024QN06017 and 2025MS06022]the Basic Scientific Research Business Fee Project for Universities in Inner Mongolia[grant numbers 2023XKJX019 and 2023XKJX024]the Central Guidance on Local Science and Technology Development Fund through[grant number 2024ZY0084].
文摘Traffic flow prediction constitutes a fundamental component of Intelligent Transportation Systems(ITS),playing a pivotal role in mitigating congestion,enhancing route optimization,and improving the utilization efficiency of roadway infrastructure.However,existingmethods struggle in complex traffic scenarios due to static spatio-temporal embedding,restricted multi-scale temporal modeling,and weak representation of local spatial interactions.This study proposes Bi-STAT+,an enhanced bidirectional spatio-temporal attention framework to address existing limitations through three principal contributions:(1)an adaptive spatio-temporal embedding module that dynamically adjusts embeddings to capture complex traffic variations;(2)frequency-domain analysis in the temporal dimension for simultaneous high-frequency details and low-frequency trend extraction;and(3)an agent attention mechanism in the spatial dimension that enhances local feature extraction through dynamic weight allocation.Extensive experiments were performed on four distinct datasets,including two publicly benchmark datasets(PEMS04 and PEMS08)and two private datasets collected from Baotou and Chengdu,China.The results demonstrate that Bi-STAT+consistently outperforms existing methods in terms of MAE,RMSE,and MAPE,while maintaining strong robustness against missing data and noise.Furthermore,the results highlight that prediction accuracy improves significantly with higher sampling rates,providing crucial insights for optimizing real-world deployment scenarios.
基金supported by the National Natural Science Foundation of China(Nos.22479092 and 22078190)。
文摘The pseudo-two-dimensional(P2D)model plays an important role in exploring physicochemical mechanisms,predicting the state of health,and improving the fast charge capability for Li-ion batteries(LIBs).However,the fast charge leads to the lithium concentration gradient in the solid and electrolyte phases and the non-uniform electrochemical reaction at the solid/electrolyte interface.In order to decouple charge transfer reactions in LIBs under dynamic conditions,understanding the spatio-temporal resolution of the P2D model is urgently required.Till now,the study of this aspect is still insufficient.This work studies the spatio-temporal resolution for dynamic/static electrochemical impedance spectroscopy(DEIS/SEIS)on multiple scales.In detail,DEIS and SEIS with spatio-temporal resolutions are used to decouple charge transfer reactions in LIBs based on the numerical solution of the P2D model in the frequency domain.The calculated results indicate that decoupling solid diffusion requires a high spatial resolution along the r-direction in particles,decoupling electrolyte diffusion and interfacial transfer reaction requires a high spatial resolution along the x-direction,and decoupling charge transfer reactions in LIBs at an extremely low state of charge(SOC)requires an extremely high temporal resolution along the t-direction.Finally,the optimal range of spatio-temporal resolutions for DEIS/SEIS is derived,and the method to decouple charge transfer reactions with spatio-temporal resolutions is developed.
文摘As one of the most crucial topics in the recommendation system field,point-of-interest(POI)recommendation aims to recommending potential interesting POIs to users.Recently,graph neural networks(GNNs)have been successfully used to model interaction and spatio-temporal information in POI recommendations,but the data sparsity of POI recommendations affects the training of GNNs.Although some existing GNN-based POI recommendation approaches try to use social relationships or user attributes to alleviate the data sparsity problem,such auxiliary information is not always available for privacy reasons.Self-supervised learning gives a new idea to alleviate the data sparsity problem,but most existing self-supervised recommendation methods cannot be directly used in the spatio-temporal graph of POI recommendations.In this paper,we propose a novel heterogeneous spatio-temporal graph contrastive learning method,HestGCL,to compensate for existing GNN-based methods’shortcomings.To model spatio-temporal information,we generate spatio-temporally specific views and design view-specific heterogeneous graph neural networks to model spatial and temporal information,respectively.To alleviate data sparsity,we propose a cross-view contrastive strategy to capture differences and correlations among views,providing more supervision signals and boosting the overall performance collaboratively.Extensive experiments on three benchmark datasets demonstrate the effectiveness of HestGCL,which significantly outperforms existing methods.
基金supported byNationalNatural Science Foundation of China,GrantNo.62402046the Beijing Forestry University Science and Technology Innovation Project under Grant No.BLX202358.
文摘Long-term traffic flow prediction is a crucial component of intelligent transportation systems within intelligent networks,requiring predictive models that balance accuracy with low-latency and lightweight computation to optimize trafficmanagement and enhance urban mobility and sustainability.However,traditional predictivemodels struggle to capture long-term temporal dependencies and are computationally intensive,limiting their practicality in real-time.Moreover,many approaches overlook the periodic characteristics inherent in traffic data,further impacting performance.To address these challenges,we introduce ST-MambaGCN,a State-Space-Based Spatio-Temporal Graph Convolution Network.Unlike conventionalmodels,ST-MambaGCN replaces the temporal attention layer withMamba,a state-space model that efficiently captures long-term dependencies with near-linear computational complexity.The model combines Chebyshev polynomial-based graph convolutional networks(GCN)to explore spatial correlations.Additionally,we incorporate a multi-temporal feature capture mechanism,where the final integrated features are generated through the Hadamard product based on learnable parameters.This mechanism explicitly models shortterm,daily,and weekly traffic patterns to enhance the network’s awareness of traffic periodicity.Extensive experiments on the PeMS04 and PeMS08 datasets demonstrate that ST-MambaGCN significantly outperforms existing benchmarks,offering substantial improvements in both prediction accuracy and computational efficiency for long-term traffic flow prediction.
基金supported by the National Natural Science Foundation of China(Grant Nos.72432004 and 72372060)。
文摘Digital manufacturing enterprises require high operational agility due to the intricate and dynamically changing nature of their tasks.The implementation of accurate and timely predictions of task bottlenecks is therefore crucial to enhancing overall efficiency.Due to task complexities and dynamic business environments,bottleneck prediction is a challenging issue.This study introduces a novel approach that constructs a task network from extensive data accumulated within a digital enterprise to identify and depict the complex interrelations among tasks.Based on this method,we develop a Bottleneck Spatio-Temporal Graph Convolutional Network (BTGCN) model based on deep learning methods that considers spatial features of the task network and temporal data of task execution and integrates the strengths of GCN and GRU.We find that GCN effectively learns and represents the complex topology of task networks to capture spatial dependencies,while GRU adapts to the dynamic changes in task data,accurately capturing temporal dependencies.Informed by the theory of constraints,the study applies the proposed BTGCN model to the prediction of task throughput bottlenecks in digital enterprises.Experimental results demonstrate that while the model has certain limitations,it can accurately extract spatio-temporal correlations from system data,offering advantages in bottleneck prediction over other benchmark models.
文摘Using skeletal information to model and recognize human actions is currently a hot research subject in the realm of Human Action Recognition(HAR).Graph Convolutional Networks(GCN)have gained popularity in this discipline due to their capacity to efficiently process graph-structured data.However,it is challenging for current models to handle distant dependencies that commonly exist between human skeleton nodes,which hinders the development of algorithms in related fields.To solve these problems,the Lightweight Multiscale Spatio-Temporal Graph Convolutional Network(LMSTGCN)is proposed.Firstly,the Lightweight Multiscale Spatial Graph Convolutional Network(LMSGCN)is constructed to capture the information in various hierarchies,and multiple inner connections between skeleton joints are captured by dividing the input features into a number of subsets along the channel direction.Secondly,the dilated convolution is incorporated into the temporal convolution to construct Lightweight Multiscale Temporal Convolutional Network(LMTCN),which allows to obtain a wider receptive field while keeping the size of the convolution kernel unchanged.Thirdly,the Spatio-Temporal Location Attention(STLAtt)module is used to identify the most informative joints in the sequence of skeletal information at a specific frame,hence improving the model’s ability to extract features and recognize actions.Finally,multi-stream data fusion input structure is used to enhance the input data and expand the feature information.Experiments on three public datasets illustrate the effectiveness of the proposed network.
基金National Natural Science Foundation of China,No.42161006Yunnan Fundamental Research Projects No.202201AT070094,No.202301BF070001-004+1 种基金Special Project for High-level Talents of Yunnan Province for Young Top Talents,No.C6213001159European Research Council(ERC)Starting-Grant STORIES,No.101040939。
文摘Due to water conflicts and allocation in the Lancang-Mekong River Basin(LMRB),the spatio-temporal differentiation of total water resources and the natural-human influence need to be clarified.This work investigated LMRB's terrestrial water storage anomaly(TWSA)and its spatio-temporal dynamics during 2002–2020.Considering the effects of natural factors and human activities,the respective contributions of climate variability and human activities to terrestrial water storage change(TWSC)were separated.Results showed that:(1)LMRB's TWSA decreased by 0.3158 cm/a.(2)TWSA showed a gradual increase in distribution from southwest of MRB to middle LMRB and from northeast of LRB to middle LMRB.TWSA positively changed in Myanmar while slightly changed in Laos and China.It negatively changed in Vietnam,Thailand and Cambodia.(3)TWSA components decreased in a descending order of soil moisture,groundwater and precipitation.(4)Natural factors had a substantial and spatial differentiated influence on TWSA over the LMRB.(5)Climate variability contributed 79%of TWSC in the LMRB while human activities contributed 21%with an increasing impact after 2008.The TWSC of upstream basin countries was found to be controlled by climate variability while Vietnam and Cambodia's TWSC has been controlled by human activities since 2012.
文摘In recent years, the large scale and frequency of severe air pollution in China has become an important consideration in the construction of livable cities and the physical and mental health of urban residents. Based on the 2016-year urban air quality index(AQI) data published by the Ministry of Environmental Protection of China, this study analyzed the spatial and temporal characteristics of air quality and its influencing factors in 338 urban units nationwide. The analysis provides an effective scientific basis for formulating national air pollution control measures. Four key results are shown. 1) Generally, air quality in the 338 cities is poor, and the average annual values for urban AQI and air pollution in 2016 were 79.58% and 21.22%, respectively. 2) The air quality index presents seasonal changes, with winter > spring > autumn > summer and a u-shaped trend. 3) The spatial distribution of the urban air quality index shows clear north-south characteristic differences and a spatial agglomeration effect; the high value area of air pollution is mainly concentrated in the North China Plain and Xinjiang Uygur Autonomous Region. 4) An evaluation of the spatial econometric model shows that differences in urban air quality are due to social, economic, and natural factors.
基金National Natural Science Foundation of China,No.71974070, No.41501593National Key R&D Project,No.2016YFA0602500Humanities and Social Sciences Foundation of Ministry of Education of China,No.19YJCZH068。
文摘Exploring the spatio-temporal dynamics of poverty is important for research on sustainable poverty reduction in China. Based on the perspective of development geography, this paper proposes a panel vector autoregressive(PVAR) model that combines the human development approach with the global indicator framework for Sustainable Development Goals(SDGs) to identify the poverty-causing and the poverty-reducing factors in China. The aim is to measure the multidimensional poverty index(MPI) of China’s provinces from 2007 to 2017, and use the exploratory spatio-temporal data analysis(ESTDA) method to reveal the characteristics of the spatio-temporal dynamics of multidimensional poverty. The results show the following:(1) The poverty-causing factors in China include the high social gross dependency ratio and crop-to-disaster ratio, and the poverty-reducing factors include the high per capita GDP, per capita social security expenditure, per capita public health expenditure, number of hospitals per 10,000 people, rate of participation in the new rural cooperative medical scheme, vegetation coverage, per capita education expenditure, number of universities, per capita research and development(R&D) expenditure, and funding per capita for cultural undertakings.(2) From 2007 to 2017, provincial income poverty(IP), health poverty(HP), cultural poverty(CP), and multidimensional poverty have been significantly reduced in China, and the overall national poverty has dropped by 5.67% annually. there is a differentiation in poverty along different dimensions in certain provinces.(3) During the study period, the local spatial pattern of multidimensional poverty between provinces showed strong spatial dynamics, and a trend of increase from the eastern to the central and western regions was noted. The MPI among provinces exhibited a strong spatial dependence over time to form a pattern of decrease from northwestern and northeastern China to the surrounding areas.(4) The spatio-temporal networks of multidimensional poverty in adjacent provinces were mainly negatively correlated, with only Shaanxi and Henan, Shaanxi and Ningxia, Qinghai and Gansu, Hubei and Anhui, Sichuan and Guizhou, and Hainan and Guangdong forming spatially strong cooperative poverty reduction relationships. These results have important reference value for the implementation of China’s poverty alleviation strategy.
基金supported by the National Natural Science Foundation of China (No.52075349)the National Natural Science Foundation of China (No.62303335)+1 种基金the Postdoctoral Researcher Program of China (No.GZC20231779)the Natural Science Foundation of Sichuan Province (No.2022NSFSC1942).
文摘Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.
基金Basic and Advanced Research Projects of CSTC,Grant/Award Number:cstc2019jcyj-zdxmX0008Science and Technology Research Program of Chongqing Municipal Education Commission,Grant/Award Numbers:KJQN202100634,KJZDK201900605National Natural Science Foundation of China,Grant/Award Number:62006065。
文摘Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.
