MVSTA: Multi-View Spatio-Temporal Correlation Awareness Network for Traffic Data Imputation

Road traffic state estimation is an essential component of intelligent transportation systems (ITSs). However, road traffic state data collected by traffic detectors are often incomplete, which can cause problems across a variety of transportation applications, such as traffic state prediction and pattern recognition. We present GA-GAN (Graph Aggregate Generative Adversarial Network), consisting of graph sample and aggregate (GraphSAGE) and a generative adversarial network (GAN), to impute missing road traffic state data. Instead of using the original road network structure, which presents the spatial information to process a graph operation, we reconstruct the road network according to the correlation coefficients of road historical data. We utilize GraphSAGE to aggregate the temporal-spatial information from the neighbors of each road in the reconstructed road network. GAN is used to generate complete traffic state data from the extracted temporal-spatial information to achieve traffic state data imputation. To illustrate the efficient performance of the model, experiments are conducted on traffic data collected from California and Seattle, Washington, showing that the proposed model outperforms state-of-the-art methods.

Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images

Traffic data plays a very important role in Intelligent Transportation Systems (ITS). ITS requires complete traffic data in transportation control, management, guidance, and evaluation. However, the traffic data collected from many different types of sensors often includes missing data due to sensor damage or data transmission error, which affects the effectiveness and reliability of ITS. In order to ensure the quality and integrity of traffic flow data, it is very important to propose a satisfying data imputation method. However, most of the existing imputation methods cannot fully consider the impact of sensor data with data missing and the spatiotemporal correlation characteristics of traffic flow on imputation results. In this paper, a traffic data imputation method is proposed based on improved low-rank matrix decomposition (ILRMD), which fully considers the influence of missing data and effectively utilizes the spatiotemporal correlation characteristics among traffic data. The proposed method uses not only the traffic data around the sensor including missing data, but also the sensor data with data missing. The information of missing data is reflected into the coefficient matrix, and the spatiotemporal correlation characteristics are applied in order to obtain more accurate imputation results. The real traffic data collected from the Caltrans Performance Measurement System (PeMS) are used to evaluate the imputation performance of the proposed method. Experiment results show that the average imputation accuracy with proposed method can be improved 87.07% compared with the SVR, ARIMA, KNN, DBN-SVR, WNN, and traditional MC methods, and it is an effective method for data imputation.

Technological breakthroughs have advanced the level of applications regarding the intelligent transportation systems (ITS). Such advancements often require human interaction, which may pose problems if the role of the humans is not properly addressed. At the same time, the number of elderly drivers is growing and the aging related deficiencies that may affect driver safety are particularly important in developing ITS systems and components. Developing future ITS components without considering the needs of this increasing special population may be a grave mistake. This paper, focusing on the older driver needs and problems within the ITS environment, reviewed and documented past and current research efforts in the US. The findings of this review indicate that even though significant research effort is focused toward the development of ITS components, very little is focused primarily on the older driver. Future research areas are identified that will assist in determining the impact of age on the various ITS components and address the specific needs of elderly drivers.

Traffic flow prediction is a core component of intelligent transportation systems, providing accurate decision support for traffic management and urban planning. Traffic flow data exhibits highly complex spatiotemporal characteristics due to the intricate spatial correlations between nodes and the significant temporal dependencies across different time intervals. Despite substantial progress in this field, several challenges still remain. Firstly, most current methods rely on Graph Convolutional Networks (GCNs) to extract spatial correlations, typically using predefined adjacency matrices. However, these matrices are inadequate for dynamically capturing the complex and evolving spatial correlations within traffic networks. Secondly, traditional prediction methods predominantly focus on short-term forecasting, which is insufficient for long-term prediction needs. Additionally, many approaches fail to fully consider the local trend information in traffic flow data which reflects short-term temporal variations. To address these issues, a novel deep learning-based traffic flow prediction model, TDMGCN, is proposed. It integrates the Transformer and a multi-graph GCN to tackle the limitations of long-term prediction and the challenges of using the predefined adjacency matrices for spatial correlation extraction. Specifically, in the temporal dimension, a convolution-based multi-head self-attention module is designed. It can not only capture long-term temporal dependencies but also extract local trend information. In the spatial dimension, the model incorporates a spatial embedding module and a multi-graph convolutional module. The former is designed to learn traffic characteristics of different nodes, and the latter is used to extract spatial correlations effectively from multiple graphs. Additionally, the model integrates the periodic features of traffic flow data to further enhance prediction accuracy. Experimental results on five real-world traffic datasets demonstrate that TDMGCN outperforms the current most advanced baseline models.

Traffic prediction is a critical component of intel-ligent transportation systems. However, highly non-linear and dynamical spatial-temporal correlations propose challenges for traffic prediction, especially long-term prediction. We propose a spatial-temporal channel-attention based graph convolutional network (STCAGCN) to improve the accuracy of both long-term and short-term traffic flow prediction. Firstly we design an attention mechanism to learn complex temporal and spatial correlations. Then we develop the stacked spatial-temporal convo-lution layer to model complex temporal and spatial correlations. Each spatial-temporal convolution layer is composed of a gated time convolution network and a graph convolution network. We develop a gated time convolution network to model non-linear temporal correlations, which process long sequences through stacked dilated convolution. Moreover, the graph convolution network exploits the hidden spatial correlations via learning self-adaptive adjacency matrix. Experiment results on real-world datasets demonstrate that the proposed STCAGCN model obtains improvements over the state-of-the-art, especially for long-term traffic flow prediction.

In the real world, data missing is inevitable in traffic data collection due to detector failures or signal interference. However, missing traffic data imputation is non-trivial since traffic data usually contains both temporal and spatial characteristics with inherent complex relations. In each time interval, the traffic measurements collected in all spatial regions can be regarded as an image with more or fewer channels. Therefore, the traffic raster data over time can be learned as videos. In this paper, we propose a novel unsupervised generative neural network for traffic raster data imputation called STVAE, which works well robustly even under different missing rates. The core idea of our model is to discover more complex spatio-temporal representations inside the traffic data under the architecture of variational autoencoder (VAE) with Sylvester normalizing flows (SNFs). After transforming the traffic raster data into multi-channel videos, a Detection-and-Calibration Block (DCB), which extends 3D gated convolution and multi-attention mechanism, is proposed to sense, extract and calibrate more flexible and accurate spatio-temporal dependencies of the original data. The experiments are employed on three real-world traffic flow datasets and demonstrate that our network STVAE achieves the lowest imputation errors and outperforms state-of-the-art traffic data imputation models.

The loss of traffic state data is a common problem in intelligent transportation system. To improve the imputation accuracy and robustness of road traffic data, a novel generative adversarial network for the imputation of road network traffic data is proposed in this paper, i.e., GAE-GAN-LSTM. The spatiotemporal characteristics were extracted using a improved graph auto-encoder (GAE), followed by a generative adversarial network (GAN) to generate the complete spatiotemporal characteristics on the basis of the missing features. The internal structure of the generator was a long short-term memory network (LSTM), and the internal structure of the discriminator was a fully connected neural network (FCN). Finally, the traffic state data could be recovered by the decoder of GAE. The experimental results revealed that the performance of the proposed method was better than that of the other methods at any data loss ratio considered. The main innovations of the proposed method include two aspects. One, an improved GAE for the imputation of road network data was presented by redefining the loss function of GAE, which could effectively extract the potential spatiotemporal features of a road network. Two, the GAN was used to generate the spatiotemporal characteristics of the traffic state data by using the strong data generation ability of GAN.KeywordsData imputationGraph auto-encoderGenerative adversarial networkRoad traffic state data

In the Intelligent Transportation System (ITS), loss of traffic data seriously influences the accuracy of decision-making of urban traffic planning and management. To solve this vital challenge, we introduce a new algebraic framework for tensor decompositions with different representation of tensor rank for traffic missing data imputation. We propose a novel tensor completion algorithm by using tensor factorization and introduce a spatial-temporal regularized constraint into the algorithm to improve the imputation performance. The simulation results with real traffic dataset demonstrate that the proposed algorithm can significantly improve the performance in terms of recovery accuracy compared with other tensor completion algorithms under different data missing patterns at all data loss rates. This also indicates that the proposed algorithm is more efficient for missing traffic data imputation by exploiting such an algebraic framework than the traditional multilinear algebraic framework for tensor decompositions.

Missing data in time series is a pervasive problem that serves as obstacles for subsequent traffic data analysis. Consequently, extensive research works have been conducted on traffic missing data imputation tasks. The state-of-the-art traffic data imputation models are mostly based on recurrent neural networks. However, these methods belong to autoregressive models which are highly susceptible to error propagation. The attention-based methods are non-autoregressive models that can avoid compounding errors and help achieve better imputation quality. Moreover, the attention-based methods in now widely applied and have achieved remarkable results, whereas their application on traffic data imputation is still limited. Thus, this paper proposes Self-Attention Graph Convolution Imputation Network (SAGCIN) for spatio-temporal traffic data. To ensure the accuracy of data imputation, it is necessary to fully capture the spatio-temporal contextual information of traffic data to impute missing values. To this end, the SAGCIN model incorporates self-attention mechanism with diffusion graph convolution network. The SAGCIN model consists of two spatio-temporal blocks with a spatio-temporal encoder and an imputation decoder. The encoder learns spatio-temporal representations specialized for traffic data imputation tasks. Based on the learned representation, the decoder performs two stages of imputation operator for missing data. A joint-optimization training approach of imputation and reconstruction is introduced for SAGCIN to perform missing value imputation for traffic data. Empirical results demonstrate that SAGCIN model outperforms state-of-the-art methods in imputation tasks on relevant real-world benchmarks.

The Indiana Department of Transportation (INDOT) is currently implementing (or has implemented) several components of Intelligent Transportation Systems (ITS). This includes a mini Advanced Traffic Management Systems (ATMS) implemented on a three-mile stretch of the Borman Expressway to evaluate advanced non-intrusive sensor systems and the associated communication infrastructure for the installation of a full-scale ATMS on the 16-mile stretch of the Borman Expressway. Potential specific ITS technologies that are either being implemented or are being considered include pre-trip information, en-route information, variable message signs, and Hoosier Helpers. It is expected that the implementation of various ITS technologies on the Borman Expressway will result in improved traffic flow, lower travel times, higher average speeds, and improved safety and environment. This study evaluated the impacts of these ITS technologies on mobility, air quality, and safety on the Borman Expressway and its vicinity. 1) Mobility - The performance of various ITS components under normal and incident conditions for the Borman Expressway Evaluation Network were simulated and the results were compared with the corresponding scenarios in the absence of these technologies. The results suggest that the network can accommodate the vehicles that divert from the Borman Expressway, indicated by the decrease in the overall network average travel time with increase in market penetration of information. Hence, providing en-route route diversion information to some users can result in significant benefits in terms of travel time savings and congestion alleviation. 2) Air Quality - The performance of various ITS components under normal and incident conditions for the Borman Expressway Evaluation Network were simulated and the resulting HC, CO, and NOx emissions were compared with the emissions under a do-nothing scenario. The same network was used for air quality impact evaluation that was used for evaluating the mobility impacts of ITS. The results obtained from the simulation experiments indicated that significant improvement in air quality can be achieved by effective implementation of various ITS technologies under normal and incident conditions. One important trend observed from the results of these experiments was that the magnitude of reduction in mobile emissions was highest under incident conditions with link closure, and lowest under normal peak-hour conditions. 3) Safety - By testing the hypothesis that secondary crashes may take place as a direct result of primary incidents or traffic congestion, safety impacts were evaluated. Logistic regression modeling was used to predict the likelihood (risk) of a primary incident being followed by

The ability of neural circuits to integrate information over time and across different cortical areas is believed an essential ingredient for information processing in the brain. Temporal and spatial correlations in cortex dynamics have independently been shown to capture these integration properties in task-dependent ways. A fundamental question remains if temporal and spatial integration properties are linked and what internal and external factors shape these correlations. Previous research on spatio-temporal correlations has been limited in duration and coverage, thus providing only an incomplete picture of their interdependence and variability. Here, we use long-term invasive EEG data to comprehensively map temporal and spatial correlations according to cortical topography, vigilance state and drug dependence over extended periods of time. We show that temporal and spatial correlations in cortical networks are intimately linked, decline under antiepileptic drug action, and break down during slow-wave sleep. Further, we report temporal correlations in human electrophysiology signals to increase with the functional hierarchy in cortex. Systematic investigation of a neural network model suggests that these dynamical features may arise when dynamics are poised near a critical point. Our results provide mechanistic and functional links between specific measurable changes in the network dynamics relevant for characterizing the brain’s changing information processing capabilities.

The ability of neural circuits to integrate information over time and across different cortical areas is believed an essential ingredient for information processing in the brain. Temporal and spatial correlations in cortex dynamics have independently been shown to capture these integration properties in task-dependent ways. A fundamental question remains if temporal and spatial integration properties are linked and what internal and external factors shape these correlations. Previous research on spatio-temporal correlations has been limited in duration and coverage, thus providing only an incomplete picture of their interdependence and variability. Here, we use long-term invasive EEG data to comprehensively map temporal and spatial correlations according to cortical topography, vigilance state and drug dependence over extended periods of time. We show that temporal and spatial correlations in cortical networks are intimately linked, decline under antiepileptic drug action, and break down during slow-wave sleep. Further, we report temporal correlations in human electrophysiology signals to increase with the functional hierarchy in cortex. Systematic investigation of a neural network model suggests that these dynamical features may arise when dynamics are poised near a critical point. Our results provide mechanistic and functional links between specific measurable changes in the network dynamics relevant for characterizing the brain's changing information processing capabilities.

Semantic understanding and prompt engineering for large-scale traffic data imputation

A great challenge for intelligent transportation systems (ITS) is missing traffic data. Traffic data are input from various transportation applications. In the past few decades, several methods for traffic temporal data imputation have been proposed. A key issue is that temporal information collected by neighbor detectors can make traffic missing data imputation more accurate. This review analyzes traffic temporal data imputation methods. Research methods, missing patterns, assumptions, imputation styles, application conditions, limitations, and public datasets are reviewed. Then, five representative methods are tested under different missing patterns and missing ratios. California performance measurement system (PeMS) data including traffic volume and speed are selected to conduct the test. Probabilistic principal component analysis performs the best under the most conditions.