Search

Timely and accurate traffic flow prediction is crucial for stabilizing road conditions, reducing environmental pollution, and mitigating economic losses. While current graph convolution methods have achieved certain results, they do not fully leverage the true advantages of graph convolution. There is still room for improvement in simultaneously addressing multi-graph convolution, optimizing graphs, and simulating road conditions. Based on this, this paper proposes MSA-GCN: Multistage Spatio-Temporal Aggregation Graph Convolutional Networks for Traffic Flow Prediction. This method overcomes the aforementioned issues by dividing the process into different stages and achieves promising prediction results. In the first stage, we construct a latent similarity adjacency matrix and address the randomness interference features in similarity features through two optimizations using the proposed ConvGRU Attention Layer (CGAL module) and the Causal Similarity Capture Module (CSC module), which includes Granger causality tests. In the second stage, we mine the potential correlation between roads using the Correlation Completion Module (CC module) to create a global correlation adjacency matrix as a complement for potential correlations. In the third stage, we utilize the proposed Auto-LRU autoencoder to pre-train various weather features, encoding them into the model's prediction process to enhance its ability to simulate the real world and improve interpretability. Finally, in the fourth stage, we fuse these features and use a Bidirectional Gated Recurrent Unit (BiGRU) to model time dependencies, outputting the prediction results through a linear layer. Our model demonstrates a performance improvement of 29.33%, 27.03%, and 23.07% on three real-world datasets (PEMSD8, LOSLOOP, and SZAREA) compared to advanced baseline methods, and various ablation experiments validate the effectiveness of each stage and module. [ABSTRACT FROM AUTHOR]

Spatio-temporal correlation and interaction are significant features of traffic accident data. To account for the spatio-temporal correlation and interaction and the ordinal nature simultaneously, spatio-temporal generalized ordered logit models with different temporal treatments are advocated to examine accident injury severities. In the context of Bayesian inference, we estimate the advocated models and compare them with traditional generalized ordered logit model and spatial generalized ordered logit model using six-year (2014-2019) accident data from the Dongguang section of Guangzhou-Shenzhen Coastal Freeway in China. The results indicate that there are significant spatio-temporal effects and interaction in the accident severity data, and that the spatio-temporal generalized ordered logit models yield low values of deviation information criterion and more reasonable parameter estimates than the generalized ordered logit and spatial generalized ordered logit models do. The estimation results reveal that covariates related to vehicle type, accident type, season, time, horizontal curvature, and bridge have significant effects on accident injury severities. The findings above demonstrate the superiority of the proposed spatio-temporal generalized ordered logit models for predicting accident severities. [ABSTRACT FROM AUTHOR]

Traffic flow prediction plays a crucial role in intelligent transportation systems (ITS), offering applications across diverse domains. However, current deep learning models face significant challenges. Real-world traffic conditions, especially during peak hours, exhibit complex spatio-temporal dynamics and intricate nonlinear relationships. Existing studies often overlook variations in traffic flow across different time periods, locations, and scenarios, resulting in prediction models lacking robustness and accuracy across diverse contexts. Furthermore, simplistic models struggle to accurately forecast traffic flow during peak periods, as they typically focus on isolated features such as traffic speed, flow rate, or occupancy rate, neglecting crucial interdependencies with other relevant factors. This paper introduces a novel approach, the peak hour embedding-based multi-feature spatio-temporal coupled traffic flow prediction model (PE-MFSTC), to address these challenges. The PE-MFSTC model incorporates peak time embedding within a multirelational synchronization graph attention network structure. The peak time-based embedding involves mapping daily, weekly, and morning/evening peak periods into low-dimensional time representations, facilitating the extraction of nonlinear spatio-temporal features. The network framework employs a multirelational synchronized graph attention network, integrating multiple traffic features and spatio-temporal sequences for learning. Additionally, a spatio-temporal dynamic fusion module (STDFM) is introduced to model correlations and dynamically adjust node weights, enhancing the model's sensitivity. Experimental evaluations on four real-world public datasets consistently demonstrate the superior performance of the PE-MFSTC model over seven state-of-the-art deep learning models. These results highlight the efficacy of the proposed model in addressing the complexities of traffic flow prediction across various scenarios. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate load forecasting, especially in the short term, is crucial for the safe and stable operation of power systems and their market participants. However, as modern power systems become increasingly complex, the challenges of short-term load forecasting are also intensifying. To address this challenge, data-driven deep learning techniques and load aggregation technologies have gradually been introduced into the field of load forecasting. However, data quality issues persist due to various factors such as sensor failures, unstable communication, and susceptibility to network attacks, leading to data gaps. Furthermore, in the domain of aggregated load forecasting, considering the potential interactions among aggregated loads can help market participants engage in cross-market transactions. However, aggregated loads often lack clear geographical locations, making it difficult to predefine graph structures. To address the issue of data quality, this study proposes a model named adversarial graph convolutional imputation network (AGCIN), combined with local and global correlations for imputation. To tackle the problem of the difficulty in predefining graph structures for aggregated loads, this study proposes a learnable adjacency matrix, which generates an adaptive adjacency matrix based on the relationships between different sequences without the need for geographical information. The experimental results demonstrate that the proposed imputation method outperforms other imputation methods in scenarios with random and continuous missing data. Additionally, the prediction accuracy of the proposed method exceeds that of several baseline methods, affirming the effectiveness of our approach in imputation and prediction, ultimately enhancing the accuracy of aggregated load forecasting. [ABSTRACT FROM AUTHOR]

The wind energy industry is witnessing a new era of extraordinary growth as the demand for renewable energy continues to grow. However, accurately predicting wind speed remains a significant challenge due to its high fluctuation and randomness. These difficulties hinder effective wind farm management and integration into the power grid. To address this issue, we propose the MRGS-LSTM model to improve the accuracy and reliability of wind speed prediction results, which considers the complex spatio-temporal correlations between features at multiple sites. First, mRMR-RF filters the input multidimensional meteorological variables and computes the feature subset with minimum information redundancy. Second, the feature map topology is constructed by quantifying the spatial distance distribution of the multiple sites and the maximum mutual information coefficient among the features. On this basis, the GraphSAGE framework is used to sample and aggregate the feature information of neighboring sites to extract spatial feature vectors. Then, the spatial feature vectors are input into the long short-term memory (LSTM) model after sliding window sampling. The LSTM model learns the temporal features of wind speed data to output the predicted results of the spatio-temporal correlation at each site. Finally, through the simulation experiments based on real historical data from the Roscoe Wind Farm in Texas, United States, we prove that our model MRGS-LSTM improves the performance of MAE by 15.43%-27.97% and RMSE by 12.57%-25.40% compared with other models of the same type. The experimental results verify the validity and superiority of our proposed model and provide a more reliable basis for the scheduling and optimization of wind farms. [ABSTRACT FROM AUTHOR]

Objective Accurate short term passenger flow prediction is of great significance to improve the operation and management efficiency of the ultra-large scale of urban rail transit network. However, the current research on deep exploration of the spatio-temporal correlations is still insufficient. Therefore, according to the spatio-temporal law of short term passenger flow, a STGCN (spatio-temporal graph convolutional neural network) model based on spatio-temporal correlation characteristics of passenger flow is proposed. Method Firstly, the spatial correlation of ultra-large scale urban rail transit network is captured by ChebyNet （Chebyshev graph convolutional network）, and the temporal correlation of the passenger flow under multi-temporal correlation characteristics is explored with the help of GRU (gated recurrent unit). Secondly, the correlation of the historical passenger flow data of the station to be predicted and that of OD (origin-destination) passenger flow data are analyzed to extract the spatio-temporal correlation deeply. Finally, a STGCN model is established in combination with the spatio-temporal correlation characteristics of the passenger flow. Result & Conclusion Taking Jiangsu Road Station of Shanghai Metro Line as an example, a short-term inbound passenger flow prediction is conducted. The result shows that the prediction accuracy with spatio-temporal correlation characteristic parameters is 16% higher than that without the parameters, indicating a better prediction effect.

With the rapid growth of population and vehicles, issues such as traffic congestion are becoming increasingly apparent. Parking guidance and information (PGI) systems are becoming more critical, with one of the most important tasks being the prediction of traffic flow in parking lots. Predicting parking traffic can effectively improve parking efficiency and alleviate traffic congestion, traffic accidents, and other problems. However, due to the complex characteristics of parking spatio-temporal data, high levels of noise, and the intricate influence of external factors, there are three challenges to predicting parking traffic in a city effectively: (1) how to better model the nonlinear, asymmetric, and complex spatial relationships among parking lots; (2) how to model the temporal autocorrelation of parking flow more accurately for each parking lot, whether periodic or aperiodic; and (3) how to model the correlation between external influences, such as holiday weekends, POIs (points of interest), and weather factors. In this context, this paper proposes a parking lot traffic prediction model based on the fusion of multifaceted spatio-temporal features (MFF-STGCN). The model consists of a feature embedding module, a spatio-temporal attention mechanism module, and a spatio-temporal convolution module. The feature embedding module embeds external features such as weekend holidays, geographic POIs, and weather features into the time series, the spatio-temporal attention mechanism module captures the dynamic spatio-temporal correlation of parking traffic, and the spatio-temporal convolution module captures the spatio-temporal features by using graph convolution and gated recursion units. Finally, the outputs of adjacent time series, daily series, and weekly series are weighted and fused to obtain the final prediction results, thus predicting the parking lot traffic flow more accurately and effectively. Results on real datasets demonstrate that the proposed model enhances prediction performance. [ABSTRACT FROM AUTHOR]

Copyright of China Sciencepaper is the property of China Sciencepaper and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate prediction of air quality change is essential for air pollution control and human daily mobility. Due to the strong spatial and temporal correlation of air quality changes, existing air quality prediction methods often face the problem of low prediction accuracy due to insufficient extraction of spatio-temporal features. In this paper, we proposed a self-tuning spatio-temporal neural network (ST2NN) to enhance air quality prediction. ST2NN model consisted of four modules. First, ST2NN model constructed a temporal feature extraction module and a spatial feature extraction module based on gated recurrent unit (GRU) and graph convolutional neural network (GCN), respectively, and the two feature extraction modules adopted a parallel structure, which could effectively extract the spatio-temporal features in data. Additionally, ST2NN model constructed a feature fusion module based on gating mechanism to delineate the contribution of spatio-temporal features to the predicted values. Further, ST2NN model constructed a Hyperband hyperparameter optimization module based on Hyperband optimization algorithm to automatically adjust the network hyperparameters. The structure of ST2NN model endowed it with excellent spatio-temporal feature extraction and parameter adaptability. ST2NN model was evaluated and compared with existing models, including convolutional long short-term memory neural network (ConvLSTM), GRU, combined convolutional neural network and long short-term memory neural network (CNN-LSTM), and GCN-LSTM for air quality index (AQI) prediction using data from twelve monitoring stations in Beijing, China. Across all four evaluation indexes, ST2NN model outperformed the comparative models, improving prediction accuracy by 0.51%-10.18% (measured using R 2 ). From the experimental results, it can be seen that ST2NN model constructed from the perspective of spatio-temporal feature extraction has better prediction performance compared with the existing air quality prediction model, which provides a new method for air quality prediction and has certain application value. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power is the property of Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Because of the high nonlinearity and complexity, it is still a challenge to forecast traffic flow accurately. Most of the existing methods, which lack the ability to model the dynamic spatio-temporal correlations of traffic flows, rely on a priori knowledge of the graph structure to capture static spatial correlations. However, spatial correlation can be dynamic and the physical structure does not reflect the true relationship between roads. To better capture complex spatio-temporal dependencies and predict traffic conditions on road networks, a new forecasting model based on Transformer and Diffusion Graph Attention Network (T-DGAN) is proposed. This model adopts the Transformer encoder-decoder architecture, where the encoder and decoder contain multiple Spatio-Temporal Convolutional Network Blocks (ST-CB) and Diffusion Graph Attention Blocks (DGA-B), which are utilized to capture the spatio-temporal dependency and the dynamic spatial correlation of traffic flow separately. In addition, an information auxiliary module is added to the decoder to summarize the traffic flow information between the encoder and the decoder. Experiments on different datasets verify that the T-DGAN model has achieved higher forecasting performance than the baseline methods. In PEMS03, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of T-DGAN to 60 min are improved by 4.28% and 3.66%, compared with the state-of-the-art model, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Arid Zone Research / Ganhanqu Yanjiu is the property of Arid Zone Research Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate traffic flow prediction plays a crucial role in the development of intelligent traffic management. Despite numerous investigations into spatio-temporal methods, achieving high accuracy in traffic flow prediction remains challenging. This challenge arises from the complex dynamic spatio-temporal correlations within the traffic road network and the limitations imposed by the selection of hyperparameters based on experiments and manual experience, which can affect the performance of the network architecture. This paper introduces a novel transformer-based adaptive graph convolutional recurrent network. The proposed network automatically infers the interdependencies among different traffic sequences and incorporates the capability to capture global spatio-temporal correlations. This enables the dynamic capture of long-range temporal correlations. Furthermore, the whale optimization algorithm is employed to efficiently design an optimal network structure that aligns with the requirements of the traffic domain and maximizes the utilization of limited computational resources. This design approach significantly enhances the model's performance and improves the accuracy of traffic flow prediction. The experimental results on four real datasets demonstrate the efficacy of our approach. In PEMS03, it improves MAE by 2.6% and RMSE by 1.4%. In PEMS04, improvements are 1.6% in MAE and 1.4% in RMSE, with a similar MAPE score to the best baseline. For PEMS07, our approach shows a 4.1% improvement in MAE and 2.2% in RMSE. On PEMS08, it surpasses the current best baseline with a 3.4% improvement in MAE and 1.6% in RMSE. These results confirm the good performance of our model in traffic flow prediction across multiple datasets. [ABSTRACT FROM AUTHOR]

An essential component of autonomous transportation system management and decision-making is precise and real-time traffic flow forecast. Predicting future traffic conditionsis a difficult undertaking because of the intricate spatio-temporal relationships involved. Existing techniques often employ separate modules to model spatio-temporal features independently, thereby neglecting the temporally and spatially heterogeneous features among nodes. Simultaneously, many existing methods overlook the long-term relationships included in traffic data, subsequently impacting prediction accuracy. We introduce a novel method to traffic flow forecasting based on the combination of the feature-augmented down-sampling dynamic graph convolutional network and multi-head attention mechanism. Our method presents a feature augmentation mechanism to integrate traffic data features at different scales. The subsampled convolutional network enhances information interaction in spatio-temporal data, and the dynamic graph convolutional network utilizes the generated graph structure to better simulate the dynamic relationships between nodes, enhancing the model's capacity for capturing spatial heterogeneity. Through the feature-enhanced subsampled dynamic graph convolutional network, the model can simultaneously capture spatio-temporal dependencies, and coupled with the process of multi-head temporal attention, it achieves long-term traffic flow forecasting. The findings demonstrate that the ADDGCN model demonstrates superior prediction capabilities on two real datasets (PEMS04 and PEMS08). Notably, for the PEMS04 dataset, compared to the best baseline, the performance of ADDGCN is improved by 2.46% in MAE and 2.90% in RMSE; for the PEMS08 dataset, compared to the best baseline, the ADDGCN performance is improved by 1.50% in RMSE, 3.46% in MAE, and 0.21% in MAPE, indicating our method's superior performance. [ABSTRACT FROM AUTHOR]

The complex environmental impact makes it difficult to predict wind speed with high precision for multiple wind turbines. Most existing research methods model the temporal dependence of wind speeds, ignoring the spatial correlation between wind turbines. In this paper, we propose a multi-wind turbine wind speed prediction model based on Weighted Diffusion Graph Convolution and Gated Attention Network (WDGCGAN). To address the strong nonlinear correlation problem among multiple wind turbines, we use the maximal information coefficient (MIC) method to calculate the correlation weights between wind turbines and construct a weighted graph for multiple wind turbines. Next, by applying Diffusion Graph Convolution (DGC) transformation to the weight matrix of the weighted graph, we obtain the spatial graph diffusion matrix of the wind farm to aggregate the high-order neighborhood information of the graph nodes. Finally, by combining the DGC with the gated attention recurrent unit (GAU), we establish a spatio-temporal model for multi-turbine wind speed prediction. Experiments on the wind farm data in Massachusetts show that the proposed method can effectively aggregate the spatio-temporal information of wind turbine nodes and improve the prediction accuracy of multiple wind speeds. In the 1h prediction task, the average RMSE of the proposed model is 28% and 33.1% lower than that of the Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN), respectively. [ABSTRACT FROM AUTHOR]

In the clutter environment, the measurement of a set of multiple extended targets, with an unknown number of targets, poses challenges in partitioning, and the computational cost is high. In particular, the multiple extended target tracking method, based on distance partition, has obvious potential estimation errors when the extended targets intersect. This paper proposes a partition algorithm, based on spatio-temporal correlation, which considers the correlation between adjacent moments of the extended target and uses this prior information to divide the measurement set into a survival target measurement set and a born target measurement set for the first time. Then, the survival target measurement set is clustered by the K-means++ algorithm, and the extended target tracking is transformed into point target tracking. The born target measurement undergoes preprocessing by the DBSCAN clustering algorithm, and then uses the directed graph with shared nearest neighbors (SNN) dividing the measurement set. The method proposed in this paper significantly reduces the number of partitions and the computational time. The effectiveness of the algorithm is demonstrated through experimental simulations. [ABSTRACT FROM AUTHOR]

A prediction method based on graph transformer (Graformer) was proposed for short-term traffic flow prediction in urban road networks, considering the spatiotemporal correlation of road network traffic status. This method transformed the traffic state prediction problem of multiple road sections into a graph node state prediction problem. For distinguishing spatial road network structures with the same structure, a graph isomorphism network with edges ( GINE) and a Transformer network to model the spatiotemporal correlation of traffic states at the road network level were combined, thereby achieving short-term traffic flow prediction for urban road networks. Specifically, the Graformer model first used the long short term memory (LSTM) network to preprocess the temporal information of the traffic data, then used the global attention mechanism based on GINE and Transformer to extract the spatial characteristics of the traffic data, and finally realized the synchronous prediction of the traffic flow of each road section of the road network. Through experimental verification using the PeMS dataset, the results show that the proposed Graformer model outperformed the comparative model in various performance indicators, demonstrating its effectiveness as a reliable and efficient short-term traffic flow prediction method for road networks. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ecology & Rural Environment is the property of Journal of Ecology & Rural Environment Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The wind energy industry is witnessing a new era of extraordinary growth as the demand for renewable energy continues to grow. However, accurately predicting wind speed remains a significant challenge due to its high fluctuation and randomness. These difficulties hinder effective wind farm management and integration into the power grid. To address this issue, we propose the MRGS-LSTM model to improve the accuracy and reliability of wind speed prediction results, which considers the complex spatio-temporal correlations between features at multiple sites. First, mRMR-RF filters the input multidimensional meteorological variables and computes the feature subset with minimum information redundancy. Second, the feature map topology is constructed by quantifying the spatial distance distribution of the multiple sites and the maximum mutual information coefficient among the features. On this basis, the GraphSAGE framework is used to sample and aggregate the feature information of neighboring sites to extract spatial feature vectors. Then, the spatial feature vectors are input into the long short-term memory (LSTM) model after sliding window sampling. The LSTM model learns the temporal features of wind speed data to output the predicted results of the spatio-temporal correlation at each site. Finally, through the simulation experiments based on real historical data from the Roscoe Wind Farm in Texas, United States, we prove that our model MRGS-LSTM improves the performance of MAE by 15.43%–27.97% and RMSE by 12.57%–25.40% compared with other models of the same type. The experimental results verify the validity and superiority of our proposed model and provide a more reliable basis for the scheduling and optimization of wind farms.

Irrigation plays a crucial role in enhancing agricultural productivity. The spatiotemporal variability and correlation between historical irrigation and grain yield not only illuminate existing challenges in irrigation, but also offer valuable insights for formulating effective irrigation strategies, which have been previously overlooked. Taking the North China Plain (NCP) as a case study, this study aims to elucidate regional divergence patterns and the dynamic evolution of the spatiotemporal relationship between grain yield and irrigation through time series analysis, GIS spatial analysis, and geographically weighted regression (GWR). The findings reveal that grain yields are higher in the northern regions of NCP compared to the southern regions, with significant variations among prefecture-level cities; maize yields slightly surpass wheat yields. Moreover, there has been a noticeable decrease in irrigation across approximately 49 % of the areas since 2004. Spatial autocorrelation analysis indicates clear spatial aggregation for both grains yields and irrigation. The coupled correlation between wheat yield and effective irrigation has shown a slight increase from 1990 to 2015, while that of maize has significantly decreased. The positive impact of irrigation on grain yield has nearly vanished since 2002. It is recommended to implement sprinkler irrigation in low-yield, low-irrigation areas in the south; deficit irrigation and water-saving technologies may benefit regions with medium yield and negative correlation with irrigation in central parts; maintaining current irrigation strategies is suggested for high-yield and high-irrigation regions. Additionally, relying solely on irrigation to boost yields is unsustainable; it is critical to adopt a combination of agricultural management practices along with planting high water-utilization efficient crop varieties. This study underscores the significance of developing rational irrigational strategies based on a comprehensive understanding of the intricate relationship between irrigation and grain yields-ensuring food security while sustaining agricultural water utilization.

Abstract In recent years, air pollution has become increasingly serious and poses a great threat to human health. Timely and accurate air quality prediction is crucial for air pollution early warning and control. Although data-driven air quality prediction methods are promising, there are still challenges in studying spatial–temporal correlations of air pollutants to design effective predictors. To address this issue, a novel model called adaptive adjacency matrix-based graph convolutional recurrent network (AAMGCRN) is proposed in this study. The model inputs Point of Interest (POI) data and meteorological data into a fully connected neural network to learn the weights of the adjacency matrix thereby constructing the self-ringing adjacency matrix and passes the pollutant data with this matrix as input to the Graph Convolutional Network (GCN) unit. Then, the GCN unit is embedded into LSTM units to learn spatio-temporal dependencies. Furthermore, temporal features are extracted using Long Short-Term Memory network (LSTM). Finally, the outputs of these two components are merged and air quality predictions are generated through a hidden layer. To evaluate the performance of the model, we conducted multi-step predictions for the hourly concentration of PM2.5, PM10 and O3 at Fangshan, Tiantan and Dongsi monitoring stations in Beijing. The experimental results show that our method achieves better predicted effects compared with other baseline models based on deep learning. In general, we designed a novel air quality prediction method and effectively addressed the shortcomings of existing studies in learning the spatio-temporal correlations of air pollutants. This method can provide more accurate air quality predictions and is expected to provide support for public health protection and government environmental decision-making.

Due to the rapid development of technologies such as cloud computing and the Internet of Things (IoT), wireless sensor networks are becoming increasingly popular in the field of environmental monitoring. Anomaly detection algorithm is often used as the main method of sensor data detection. The development and application of IoT technology has led to a significant increase in data traffic. However, current anomaly detection methods are difficult to effectively detect heterogeneous data sequences from multiple sources. In this study, the sensor monitoring model of an intelligent greenhouse is constructed by using the spatio-temporal correlation anomaly detection algorithm in edge computing. The data is chunked by a sliding window to reduce the error of one-sided estimation of single data on the detection results. The spatial correlation anomaly detection algorithm is formed on the basis of the temporal correlation detection algorithm, fusing the two algorithms with the edge computation to construct a multi-source multi-dimensional data anomaly detection model. The results of the time-related anomaly detection algorithm experiment showed that the F1-score of the algorithm was 91.26%. Compared with other methods, the false alarm rate of spatial correlation anomaly detection algorithm was reduced by 56.50% ~ 83.45%, and F1-score was increased by 1.37% ~ 22.25%. In the case of big data, the detection time of the sensor monitoring model was 0.47s, the required energy consumption was reduced by 36.75% ~ 79.20%, and the delay time was the least. The anomaly detection algorithm in this study is related to time and space, which effectively improves the detection rate and detection accuracy, thus reducing the computing load of the cloud platform, and is superior to the deep learning method in processing delay.

In recent years, time series forecasting has been widely used in various fields, especially in financial markets. Stock trend forecasting has become one of the most common and complex challenges faced by investors and researchers. However, much of the current research relies primarily on single-granularity stock data for forecasting, with relatively few studies on multi-granularity data and fewer studies on spatial correlation of multi-granularity data. This inherent limitation restricts the comprehensive extraction of valuable information. To address this challenge, we propose the Multi-Granularity Deep Spatio-Temporal Correlation Framework (MDSTCF). Our approach combines the strengths of a multi-granularity residual learning, gated recurrent units, and graph attention networks to extract spatio-temporal information specific to each granularity. Subsequently, predictions at each granularity are generated through the prediction layer. Finally, a soft attention mechanism is employed to assign weights to the predictions at each granularity to obtain the final result. Comprehensive experiments conducted on tow stock datasets show that the proposed forecasting model improves the F1 score by about 7.88% and 11.2%, and the cumulative relative returns are close to 80% and 40%, respectively, compared to the previously studied time series forecasting models. The results clearly indicates that fusing multi-granularity information can significantly improve the performance of time series forecasting.

Accurately predicting traffic flow is paramount for the efficient operation of transportation systems. The key to enhancing prediction accuracy lies in effectively mining the intricate spatio-temporal correlations within traffic flow data. However, traditional traffic flow prediction methods that combine Graph Convolutional Network and Recurrent Neural Network have limitations in capturing comprehensive spatial correlation information and face challenges in modeling long-term temporal dependencies, consequently leading to suboptimal prediction performance. This study proposes a hybrid traffic flow prediction model based on fusion graph convolutional network and enhanced gate recurrent unit. Initially, a fusion graph structure is constructed based on adjacency graph and adaptive graph to better represent the correlations between nodes in the road network. Subsequently, the stacked fusion graph convolution module is utilized to capture multi-level spatial correlations and the enhanced gated recurrent unit is applied to extract multi-scale temporal correlations. In addition, the model integrates the extracted spatio-temporal features with the direct features through residual connection units, and utilizes the fused features for prediction, achieving superior predictive performance. The experimental results from four authentic datasets demonstrate that our proposed model outperforms state-of-the-art baseline models, showcasing an average enhancement of 3% in Mean Absolute Error(MAE), 3.3% in Root Mean Square Error(RMSE), and 2.7% in Mean Absolute Percentage Error(MAPE) across the four datasets.

Timely and accurate traffic flow prediction is crucial for stabilizing road conditions, reducing environmental pollution, and mitigating economic losses. While current graph convolution methods have achieved certain results, they do not fully leverage the true advantages of graph convolution. There is still room for improvement in simultaneously addressing multi-graph convolution, optimizing graphs, and simulating road conditions. Based on this, this paper proposes MSA-GCN: Multistage Spatio-Temporal Aggregation Graph Convolutional Networks for Traffic Flow Prediction. This method overcomes the aforementioned issues by dividing the process into different stages and achieves promising prediction results. In the first stage, we construct a latent similarity adjacency matrix and address the randomness interference features in similarity features through two optimizations using the proposed ConvGRU Attention Layer (CGAL module) and the Causal Similarity Capture Module (CSC module), which includes Granger causality tests. In the second stage, we mine the potential correlation between roads using the Correlation Completion Module (CC module) to create a global correlation adjacency matrix as a complement for potential correlations. In the third stage, we utilize the proposed Auto-LRU autoencoder to pre-train various weather features, encoding them into the model’s prediction process to enhance its ability to simulate the real world and improve interpretability. Finally, in the fourth stage, we fuse these features and use a Bidirectional Gated Recurrent Unit (BiGRU) to model time dependencies, outputting the prediction results through a linear layer. Our model demonstrates a performance improvement of 29.33%, 27.03%, and 23.07% on three real-world datasets (PEMSD8, LOSLOOP, and SZAREA) compared to advanced baseline methods, and various ablation experiments validate the effectiveness of each stage and module.

Accurate load forecasting, especially in the short term, is crucial for the safe and stable operation of power systems and their market participants. However, as modern power systems become increasingly complex, the challenges of short-term load forecasting are also intensifying. To address this challenge, data-driven deep learning techniques and load aggregation technologies have gradually been introduced into the field of load forecasting. However, data quality issues persist due to various factors such as sensor failures, unstable communication, and susceptibility to network attacks, leading to data gaps. Furthermore, in the domain of aggregated load forecasting, considering the potential interactions among aggregated loads can help market participants engage in cross-market transactions. However, aggregated loads often lack clear geographical locations, making it difficult to predefine graph structures. To address the issue of data quality, this study proposes a model named adversarial graph convolutional imputation network (AGCIN), combined with local and global correlations for imputation. To tackle the problem of the difficulty in predefining graph structures for aggregated loads, this study proposes a learnable adjacency matrix, which generates an adaptive adjacency matrix based on the relationships between different sequences without the need for geographical information. The experimental results demonstrate that the proposed imputation method outperforms other imputation methods in scenarios with random and continuous missing data. Additionally, the prediction accuracy of the proposed method exceeds that of several baseline methods, affirming the effectiveness of our approach in imputation and prediction, ultimately enhancing the accuracy of aggregated load forecasting.

Space infrared (IR) target recognition has always been a key issue in the field of space technology. The imaging distance is long, the target is weak, and the feature discrimination is low, making it difficult to distinguish between high-threat targets and decoys. However, most existing methods ignore the fuzziness of multi-dimensional features, and their performance mainly depends on the accuracy of feature extraction, with certain limitations in handling uncertainty and noise. This article proposes a space IR dim target fusion recognition method, which is based on fuzzy comprehensive of spatio-temporal correlation. First, we obtained multi-dimensional IR features of the target through multi-time and multi-spectral detectors, then we established and calculated the adaptive fuzzy-membership function of the features. Next, we applied the entropy weight method to ascertain the objective fusion weights of each feature and computed the spatially fuzzified fusion judgments for the targets. Finally, the fuzzy comprehensive function was used to perform temporal recursive judgment, and the ultimate fusion recognition result was obtained by integrating the results of each temporal recursive judgment. The simulation and comparative experimental results indicate that the proposed method improved the accuracy and robustness of IR dim target recognition in complex environments. Under ideal conditions, it can achieve an accuracy of 88.0% and a recall of 97.5% for the real target. In addition, this article also analyzes the impact of fusion feature combinations, fusion frame counts, different feature extraction errors, and feature database size on recognition performance. The research in this article can enable space-based IR detection systems to make more accurate and stable decisions, promoting defense capabilities and ensuring space security. [ABSTRACT FROM AUTHOR]

Optimizing the energy consumption of an MEC (Multi-Access Edge Computing) system is a crucial challenge for operation cost reduction and environmental conservation. In this paper, we address an MECS (MEC Server) sleep control problem that aims to reduce the energy consumption of the system while providing users with a reasonable service delay by adjusting the number of active MECSs according to the load imposed on the system. To tackle the problem, we identify two crucial issues that influence the design of an effective sleep control technique and propose methods to address each of these issues. The first issue is accurately predicting the system load. Changes in system load are spatio-temporally correlated among MECSs. By leveraging such correlation information with STGCN (Spatio-Temporal Graph Convolutional Network), we enhance the prediction accuracy of task arrival rates for each MECS. The second issue is rapidly selecting MECSs to sleep when the load distribution over an MEC system is given. The problem of choosing sleep MECS is a combinatorial optimization problem with high time complexity. To address the issue, we employ a genetic algorithm and quickly determine the optimal sleep MECS with the predicted load information for each MECS. Through simulation studies, we verify that compared to the LSTM (Long Short-Term Memory)-based method, our method increases the energy efficiency of an MEC system while providing a compatible service delay. [ABSTRACT FROM AUTHOR]

Wireless sensor devices are affected by internal constraints and the external environment, generating abnormal data. Currently, many anomaly detection schemes ignore the correlation between screening nodes, wasting resources due to excessive communication. Therefore, this paper proposes a distributed anomaly detection scheme based on adaptive grouping using the correlation between nodes in wireless sensor networks. Limiting the scope of collaboration between nodes can reduce the waste of resources due to excessive communication. Since the computing resources of sensor nodes are limited, an edge-cloud framework is established. The scheme uses Spatio-temporal correlation and graph theory for wireless sensor networks to determine node groups with solid correlations on the cloud server. Based on the grouping results, anomaly detection is implemented locally. A Bayesian network model is constructed at the node within the group, and outlier detection is realized by inference on nodes. A correlation consistency evaluation method is proposed to improve anomaly detection accuracy to check the data consistency on the cluster head. The proposed scheme is verified by a generated data set and the real data of Intel Berkeley Research Lab. The effectiveness of the proposed method is verified by comparing it with three existing algorithms. Experimental results show that the method improves detection accuracy and reduces false detection. [ABSTRACT FROM AUTHOR]

Accurate power prediction of photovoltaic plant is of great significance for the stable and safe operation of power system. In order to fully exploit the spatio-temporal information features of multiple plants in the region and improve the prediction accuracy of plants in the region, a power prediction approach for photovoltaic plants based on graph convolutional network long short-term memory (GCN-LSTM) was proposed. Firstly, the approach used K-means clustering algorithm (K-means) to divide the total power of plants in the region into three different weather types. Then, in order to predict the total power in the region, a hypothetical plant was constructed, and GCN was used to extract the features of dynamic spatial correlation information between plants. Finally, the time series formed by graph convolutional network (GCN) mining information was used as the input of long short-term memory network (LSTM) to extract the time information features of the plant, so as to predict the photovoltaic power in the region. The experimental results show that this approach can fully excavate the spatio-temporal correlation information between plants, and accurately predict the output power of photovoltaic plants. It can also provide certain reference value for ensuring the stable and safe operation of the power system. [ABSTRACT FROM AUTHOR]

Nowadays, to improve animal well being in livestock farming application, a wireless video sensor network (WVSN) can be deployed to early detect injury and monitor animals. They are composed of small embedded video and camera motes that capture video frames periodically and send them to a specific node called a sink. Sending all the captured images to the sink consumes a lot of energy on every sensor and may cause a bottleneck at the sink level. Energy consumption and bandwidth limitation are two important challenges in WVSNs because of the limited energy resources of the nodes and the medium scarcity. In this work, we introduce two mechanisms to reduce the overall number of frames sensed and sent to the sink. The first approach is applied on each sensor node, where the FRABID algorithm, a joint data reduction, and frame rate adaptation on sensing and transmission phases mechanism is introduced. This approach reduces the number of sensed frames based on a similarity method. The aim is to adapt the number of sensed frames based on the degree of difference between two consecutive sensed frames in each period. This adaptation technique maintains the accuracy of the video while capturing frames holding new information. This approach is validated through simulations using real data-sets from video sensors (Wang et al. in: 2014 IEEE conference on computer vision and pattern recognition workshops, pp 393–400, 2014). The results show that the amount of sensed data is reduced by more than 70% compared to a recent algorithm in Christian et al. (Multimed Tools Appl 79(3):1801–1819, 2020) while guaranteeing the detection of all the critical events at the sensor node level. The second approach exploits the Spatio-temporal correlation between neighboring nodes to reduce the number of captured frames. For that purpose, Synchronization with Frame Rate Adaptation SFRA algorithm is introduced where overlapping nodes capture frames in a synchronized fashion every N - 1 periods, where N is the number of overlapping sensor nodes. The results show more than 90% data reduction, surpassing other techniques in the literature at the level of the number of sensed frames by 20% at least. [ABSTRACT FROM AUTHOR]

Accurate prediction of short-term passengers' origin and destination (OD) demands is key to efficient operation and management of urban rail transit (URT), especially in the case of congestion or an incident. However, short-term OD demand forecasting is more challenging than passenger flow forecasting, due to its uncertainty and high dimensions. So far, most OD prediction models capture the spatio-temporal dependencies of OD flow by means of training models on historical data, but what characteristics and laws influence the performance of OD prediction are still unknown. In this paper, we propose temporal Pearson correlation coefficients and approximate entropy, as well as spatial correlations, as indicators to reflect the inherent time–space correlations and complexity of the OD flow. Then, by analyzing automatic fare collection data of the Beijing and Shanghai URT system, this paper deeply discusses the relationships between the spatio-temporal correlations and complexity of the OD flow and the predictive performances of different models with regard to different intervals. Finally, this paper proposes the predictable problem of travel demands and points out that the spatial correlations of the OD matrix are more important than the temporal correlations and complexity in the short-term prediction of travel demands. In particular, the number of principal components of the OD flow can be a key indicator to measure the forecasting performance of a model. A reasonable interval is very important for short-term OD forecasting, and in the Beijing URT system, 30 min is a preferable choice for workdays and 50 min for weekends. All these findings are beneficial to guide users to build a suitable model or improve the existing model to obtain better prediction performances. [ABSTRACT FROM AUTHOR]

With the rapid growth of population and vehicles, issues such as traffic congestion are becoming increasingly apparent. Parking guidance and information (PGI) systems are becoming more critical, with one of the most important tasks being the prediction of traffic flow in parking lots. Predicting parking traffic can effectively improve parking efficiency and alleviate traffic congestion, traffic accidents, and other problems. However, due to the complex characteristics of parking spatio-temporal data, high levels of noise, and the intricate influence of external factors, there are three challenges to predicting parking traffic in a city effectively: (1) how to better model the nonlinear, asymmetric, and complex spatial relationships among parking lots; (2) how to model the temporal autocorrelation of parking flow more accurately for each parking lot, whether periodic or aperiodic; and (3) how to model the correlation between external influences, such as holiday weekends, POIs (points of interest), and weather factors. In this context, this paper proposes a parking lot traffic prediction model based on the fusion of multifaceted spatio-temporal features (MFF-STGCN). The model consists of a feature embedding module, a spatio-temporal attention mechanism module, and a spatio-temporal convolution module. The feature embedding module embeds external features such as weekend holidays, geographic POIs, and weather features into the time series, the spatio-temporal attention mechanism module captures the dynamic spatio-temporal correlation of parking traffic, and the spatio-temporal convolution module captures the spatio-temporal features by using graph convolution and gated recursion units. Finally, the outputs of adjacent time series, daily series, and weekly series are weighted and fused to obtain the final prediction results, thus predicting the parking lot traffic flow more accurately and effectively. Results on real datasets demonstrate that the proposed model enhances prediction performance.

The problem of traffic flow forecasting has multi-source heterogeneity.The traffic flow in the future is not only related to the flow at the previous moment, but also affected by heterogeneous spatio-temporal data such as the relationship between urban regions, weather conditions and POI (point of interest).To solve this problem, a traffic flow prediction model based on multi-source heterogeneous spatio-temporal data fusion was proposed, which was called MHFSTNet (multi-source heterogeneous fusion spatio-temporal network).Firstly, this model used clustering methods to obtain different traffic patterns in urban areas, and utilized various methods such as concatenation, weight addition, and attention mechanism to integrate spatio-temporal data of multiple modalities, including traffic flow, location relationships between urban areas, weather, POI and the time of day.Deep learning methods were used to uniformly model heterogeneous data and predict traffic flow in the future.Experiments were conducted on three real-world traffic datasets, TaxiBJ, TaxiNYC and BikeNYC datasets.The results showed that MHF-STNet achieved the best performance compared with some classic traffic flow prediction models, which verified the effectiveness of MHF-STNet for unified modeling of heterogeneous spatio-temporal data.

High-precision water quality prediction plays a vital role in preventing and controlling river pollution. However, river water's highly nonlinear and complex spatio-temporal dependencies pose significant challenges to water quality prediction tasks. In order to capture the spatial and temporal characteristics of water quality data simultaneously, this paper combines deep learning algorithms for river water quality prediction in the river network area of Jiangnan Plain, China. A water quality prediction method based on graph convolutional network (GCN) and long short-term memory neural network (LSTM), namely spatio-temporal graph convolutional network model (ST-GCN), is proposed. Specifically, the spatio-temporal graph is constructed based on the spatio-temporal correlation between river stations, the spatial features in the river network are extracted using GCN, and the temporal correlation of water quality data is obtained by integrating LSTM. The model was evaluated using R2, MAE, and RMSE, and the experimental results were 0.977, 0.238, and 0.291, respectively. Compared with traditional water quality prediction models, the ST-GCN model has significantly improved prediction accuracy, better stability, and generalization ability. HIGHLIGHTS The spatio-temporal graph is used to characterize the spatio-temporal correlation of different monitoring stations.; Based on the GCN and the LSTM, the ST-GCN model is suitable for extracting spatial and temporal features in graph data.; In terms of river water quality prediction, the model has significantly improved performance compared with the five baseline models.;

Traffic predicting is a critical component of modern intelligent transportation systems for traffic management and control. However, the traffic flow is complex. On one hand, the urban road structure is highly correlative, and there often exists a nonlinear structural dependence between different roads. On the other hand, traffic flow data often change dynamically over time. In recent years, many studies have tried to use deep learning methods to extract complex structural features in traffic flow. However, the process of local feature extraction still lacks flexibility, and ignores the dynamic variability as well as the correlation of spatio-temporal features. To this end, this paper proposes a new traffic prediction method integrating graph wavelet and attention mechanism. This method uses wavelet transform and an adaptive matrix to extract local and global spatial features of traffic flow respectively, and combines the improved recurrent neural network to extract local temporal characteristic information. Meanwhile, the attention mechanism is adopted in this method to capture the temporal and spatial dynamic variability. Then this method applies a spatio-temporal feature fusion mechanism to fusing local and global temporal and spatial features. Experimental results show that this method can extract spatial and temporal features of real traffic datasets well, and it outperforms the existing methods.

Optimizingthe cache hit rate in a multi-access edge computing (MEC) system is essential in increasing the utility of a system. A pivotal challenge within this context lies in predicting the popularity of a service. However, accurately predicting popular services for each MEC server (MECS) is hindered by the dynamic nature of user preferences in both time and space, coupled with the necessity for real-time adaptability. In this paper, we address this challenge by employing the Convolutional Long Short-Term Memory (ConvLSTM) model, which can capture both temporal and spatial correlations inherent in service request patterns. Our proposed methodology leverages ConvLSTM for service popularity prediction by modeling the distribution of service popularity in a MEC system as a heatmap image. Additionally, we propose a procedure that predicts service popularity in each MECS through a sequence of heatmap images. Through simulation studies using real-world datasets, we compare the performance of our method with that of the LSTM-based method. In the LSTM-based method, each MECS predicts the service popularity independently. On the contrary, our method takes a holistic approach by considering spatio-temporal correlations among MECSs during prediction. As a result, our method increases the average cache hit rate by more than 6.97 % compared to the LSTM-based method. From an implementation standpoint, our method requires only one ConvLSTM model while the LSTM-based method requires at least one LSTM model for each MECS. Thus, compared to the LSTM-based method, our method reduces the deep learning model parameters by 32.15%. [ABSTRACT FROM AUTHOR]

To better fit the actual data, this paper will consider both spatio-temporal correlation and heterogeneity to build the model. In order to overcome the "curse of dimensionality" problem in the nonparametric method, we improve the estimation method of the single-index model and combine it with the correlation and heterogeneity of the spatio-temporal model to obtain a good estimation method. In this paper, assuming that the spatio-temporal process obeys the α mixing condition, a nonparametric procedure is developed for estimating the variance function based on a fully nonparametric function or dimensional reduction structure, and the resulting estimator is consistent. Then, a reweighting estimation of the parametric component can be obtained via taking the estimated variance function into account. The rate of convergence and the asymptotic normality of the new estimators are established under mild conditions. Simulation studies are conducted to evaluate the efficacy of the proposed methodologies, and a case study about the estimation of the air quality evaluation index in Nanjing is provided for illustration. [ABSTRACT FROM AUTHOR]

The increasing popularity of portable smart devices has led to the emergence of vehicular crowdsensing as a novel approach for real-time sensing and environmental data collection, garnering significant attention across various domains. Within vehicular crowdsensing, task assignment stands as a fundamental research challenge. As the number of vehicle users and perceived tasks grows, the design of efficient task assignment schemes becomes crucial. However, existing research solely focuses on task deadlines, neglecting the importance of task duration. Additionally, the majority of privacy protection mechanisms in the current task assignment process emphasize safeguarding user location information but overlook the protection of user-perceived duration. This lack of protection exposes users to potential time-aware inference attacks, enabling attackers to deduce user schedules and device information. To address these issues in opportunistic task assignment for vehicular crowdsensing, this paper presents the minimum number of participants required under the constraint of probability coverage and proposes the User-Based Task Assignment (UBTA) mechanism, which selects the smallest set of participants to minimize the payment cost while measuring the probability of accomplishing perceived tasks by user combinations. To ensure privacy protection during opportunistic task assignment, a privacy protection method based on differential privacy is introduced. This method fuzzifies the sensing duration of vehicle users and calculates the probability of vehicle users completing sensing tasks, thus avoiding the exposure of users' sensitive data while effectively assigning tasks. The efficacy of the proposed algorithm is demonstrated through theoretical analysis and a comprehensive set of simulation experiments. [ABSTRACT FROM AUTHOR]

Accurate traffic flow prediction plays a crucial role in the development of intelligent traffic management. Despite numerous investigations into spatio-temporal methods, achieving high accuracy in traffic flow prediction remains challenging. This challenge arises from the complex dynamic spatio-temporal correlations within the traffic road network and the limitations imposed by the selection of hyperparameters based on experiments and manual experience, which can affect the performance of the network architecture. This paper introduces a novel transformer-based adaptive graph convolutional recurrent network. The proposed network automatically infers the interdependencies among different traffic sequences and incorporates the capability to capture global spatio-temporal correlations. This enables the dynamic capture of long-range temporal correlations. Furthermore, the whale optimization algorithm is employed to efficiently design an optimal network structure that aligns with the requirements of the traffic domain and maximizes the utilization of limited computational resources. This design approach significantly enhances the model’s performance and improves the accuracy of traffic flow prediction. The experimental results on four real datasets demonstrate the efficacy of our approach. In PEMS03, it improves MAE by 2.6% and RMSE by 1.4%. In PEMS04, improvements are 1.6% in MAE and 1.4% in RMSE, with a similar MAPE score to the best baseline. For PEMS07, our approach shows a 4.1% improvement in MAE and 2.2% in RMSE. On PEMS08, it surpasses the current best baseline with a 3.4% improvement in MAE and 1.6% in RMSE. These results confirm the good performance of our model in traffic flow prediction across multiple datasets.

An essential component of autonomous transportation system management and decision-making is precise and real-time traffic flow forecast. Predicting future traffic conditionsis a difficult undertaking because of the intricate spatio-temporal relationships involved. Existing techniques often employ separate modules to model spatio-temporal features independently, thereby neglecting the temporally and spatially heterogeneous features among nodes. Simultaneously, many existing methods overlook the long-term relationships included in traffic data, subsequently impacting prediction accuracy. We introduce a novel method to traffic flow forecasting based on the combination of the feature-augmented down-sampling dynamic graph convolutional network and multi-head attention mechanism. Our method presents a feature augmentation mechanism to integrate traffic data features at different scales. The subsampled convolutional network enhances information interaction in spatio-temporal data, and the dynamic graph convolutional network utilizes the generated graph structure to better simulate the dynamic relationships between nodes, enhancing the model’s capacity for capturing spatial heterogeneity. Through the feature-enhanced subsampled dynamic graph convolutional network, the model can simultaneously capture spatio-temporal dependencies, and coupled with the process of multi-head temporal attention, it achieves long-term traffic flow forecasting. The findings demonstrate that the ADDGCN model demonstrates superior prediction capabilities on two real datasets (PEMS04 and PEMS08). Notably, for the PEMS04 dataset, compared to the best baseline, the performance of ADDGCN is improved by 2.46% in MAE and 2.90% in RMSE; for the PEMS08 dataset, compared to the best baseline, the ADDGCN performance is improved by 1.50% in RMSE, 3.46% in MAE, and 0.21% in MAPE, indicating our method’s superior performance.

The complex environmental impact makes it difficult to predict wind speed with high precision for multiple wind turbines. Most existing research methods model the temporal dependence of wind speeds, ignoring the spatial correlation between wind turbines. In this paper, we propose a multi-wind turbine wind speed prediction model based on Weighted Diffusion Graph Convolution and Gated Attention Network (WDGCGAN). To address the strong nonlinear correlation problem among multiple wind turbines, we use the maximal information coefficient (MIC) method to calculate the correlation weights between wind turbines and construct a weighted graph for multiple wind turbines. Next, by applying Diffusion Graph Convolution (DGC) transformation to the weight matrix of the weighted graph, we obtain the spatial graph diffusion matrix of the wind farm to aggregate the high-order neighborhood information of the graph nodes. Finally, by combining the DGC with the gated attention recurrent unit (GAU), we establish a spatio-temporal model for multi-turbine wind speed prediction. Experiments on the wind farm data in Massachusetts show that the proposed method can effectively aggregate the spatio-temporal information of wind turbine nodes and improve the prediction accuracy of multiple wind speeds. In the 1h prediction task, the average RMSE of the proposed model is 28% and 33.1% lower than that of the Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN), respectively.

In the clutter environment, the measurement of a set of multiple extended targets, with an unknown number of targets, poses challenges in partitioning, and the computational cost is high. In particular, the multiple extended target tracking method, based on distance partition, has obvious potential estimation errors when the extended targets intersect. This paper proposes a partition algorithm, based on spatio-temporal correlation, which considers the correlation between adjacent moments of the extended target and uses this prior information to divide the measurement set into a survival target measurement set and a born target measurement set for the first time. Then, the survival target measurement set is clustered by the K-means++ algorithm, and the extended target tracking is transformed into point target tracking. The born target measurement undergoes preprocessing by the DBSCAN clustering algorithm, and then uses the directed graph with shared nearest neighbors (SNN) dividing the measurement set. The method proposed in this paper significantly reduces the number of partitions and the computational time. The effectiveness of the algorithm is demonstrated through experimental simulations.

Accurate traffic flow forecasting is a prerequisite guarantee for the realization of intelligent transportation. Due to the complex time and space features of traffic flow, its forecasting has always been a research hotspot in this field. Aiming at the difficulty of capturing and modelling the temporal and spatial correlation and dynamic features of traffic flow, this paper proposes a novel graph convolutional network traffic flow forecasting model (STAGCN) based on the temporal and spatial attention mechanism. STAGCN model is mainly composed of three modules: Spatio-temporal Attention (STA-Block), Graph Convolutional Network (GCN) and Standard Convolutional Network (CN), model the periodicity, spatial correlation and time dependence of traffic flow respectively. STA-Block module models the spatio-temporal correlation between different time steps through the spatio-temporal attention mechanism and gating fusion mechanism, and uses GCN and CN to capture the spatial and temporal features of traffic flow respectively. Finally, the output of the three components is predicted through a gated fusion mechanism. A large number of experiments have been conducted on two data sets of PeMS. The experimental results demonstrate that compared with the baseline method, the STAGCN model proposed in this paper has better forecasting performance. [ABSTRACT FROM AUTHOR]

Geospatial factors, because of their spatio-temporal correlations with demand-driven limited service, offer to improve urban planning decisions and expand the knowledge base in cities. Spatio-temporal analyses require an efficient and comprehensible visualization and explanation in order to analyze and understand geospatial relationships in urban areas. The aim of our research is to support domain experts in these analyses with user-oriented geovisualization. In this article, we propose concepts towards a semantic comparison visualization, which combines a visual analysis view and a visual explanation view. The visual analysis view is a knowledge-oriented view that focuses on analyzing resulting spatio-temporal correlations. The visual explanation view is an understanding-oriented view that focuses on explaining the underlying complex analysis process of geospatial factors and spatio-temporal correlations. We define general requirements for this aim and validate and evaluate our concepts related to these requirements. The results show the benefit of our concepts, but, at the same time, they also point to limitations and potential for optimization in further work. [ABSTRACT FROM AUTHOR]