JS-STDGN: A Spatial-Temporal Dynamic Graph Network Using JS-Graph for Traffic Prediction

Accurate traffic prediction is crucial to alleviating traffic congestion in cities. Existing physical sensor-based traffic data acquisition methods have high transmission costs, serious traffic information redundancy, and large calculation volumes for spatiotemporal data processing, thus making it difficult to ensure accuracy and real-time traffic prediction. With the increasing resolution of UAV imagery, the use of unmanned aerial vehicles (UAV) imagery to obtain traffic information has become a hot spot. Still, analyzing and predicting traffic status after extracting traffic information is neglected. We develop a framework for traffic speed extraction and prediction based on UAV imagery processing, which consists of two parts: a traffic information extraction module based on UAV imagery recognition and a traffic speed prediction module based on deep learning. First, we use deep learning methods to automate the extraction of road information, implement vehicle recognition using convolutional neural networks and calculate the average speed of road sections based on panchromatic and multispectral image matching to construct a traffic prediction dataset. Then, we propose an attention-enhanced traffic speed prediction module that considers the spatiotemporal characteristics of traffic data and increases the weights of key roads by extracting important fine-grained spatiotemporal features twice to improve the prediction accuracy of the target roads. Finally, we validate the effectiveness of the proposed method on real data. Compared with the baseline algorithm, our algorithm achieves the best prediction performance regarding accuracy and stability.

Traffic parameter forecasting is critical to effective traffic management but is a challenging task due to the stochasticity of traffic flow characteristics, especially in urban road networks. Traffic networks can be affected by external factors, such as weather, events, accidents, and road construction works. The impact of these factors can affect traffic flow parameters by influencing travel time, density, occupancy, and operating speed. Although deep neural networks (DNNs) have recently shown promising signs in traffic prediction using big data, there still exists the issue of maximizing the use of the model capabilities by using big data sources. This paper proposes an improved urban traffic speed prediction approach involving input-level data fusion and deep learning. Motivated by deep learning prediction methods, we propose a Long Short-Term Memory Neural Network (LSTM-NN) for traffic speed prediction that combines traffic and weather datasets on an urban road network in Greater Manchester, United Kingdom. The experimental results substantiate the value of the approach when compared to the use of traffic-only data sources for traffic speed prediction.

Short-term freeway traffic speed prediction is essential to improving mobility and roadway safety. It has been a challenging and unresolved issue. Traffic speed prediction can be applied to enhance the intelligent freeway traffic management and control for applications such as operational and regulation planning. For example, with more reliable traffic speed prediction, the advanced traveler information system can provide travelers with predictive travel time information and optimal routing, which allows them to arrange their schedules accordingly. Moreover, traffic managers can use the predicted information to deploy various traffic management strategies to increase system efficiency. In this paper, a hybrid empirical mode decomposition (EMD) and autoregressive integrated moving average (ARIMA) (or EMD-ARIMA) approach was developed to predict the short-term traffic speed on freeways. In general, there were three stages in the hybrid EMD-ARIMA forecasting framework. The first was the EMD stage, which decomposed the freeway traffic speed time series data into a number of intrinsic mode function (IMF) components and a residue. The second stage was to find the appropriate ARIMA model for each IMF and residue and then make predictions on the basis of the appropriate ARIMA model. The third stage was to combine the prediction results of each IMF and residue to make the predictions. The experimental results indicated that the proposed hybrid EMD-ARIMA framework was capable of predicting short-term freeway traffic speed with high accuracy.

Accurate traffic forecasting is essential for intelligent transportation system management and control. Due to the highly complex spatiotemporal (ST) correlation of real-world road networks, dynamic and long-term traffic prediction presents many challenges. We propose a traffic speed prediction model based on dynamic structural prior (DSP) ST graph attention networks. We provide a structural prior graph, namely, dual graph convolution, which combines spatial and contextual subgraphs to enable the discovery of the non-Euclidean spatial correlation and potential contextual similarity of road networks. Moreover, to dynamically extract the ST correlation, this article employs a multihead self-attention temporal convolution module to capture the temporal correlation and a graph attention convolution module to extract the spatial correlation. The prediction output is generated by stacking multiple ST blocks. Experimental results on two real-world traffic datasets demonstrate that DSP-ST outperforms existing mainstream baselines, which can provide references for traffic management departments.

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction

For providing drivers with robust traffic information and Optimizing the energy management of Hybrid Electric Vehicles (HEVs), it is important to predict traffic information accurately with past traffic information. As acquisition of the traffic information have been easier by the development of Intelligent Transportation System (ITS), active study on traffic prediction is currently underway. Multi-Layer Perceptron (MLP) model have been widely utilized for predicting traffic information since it is appropriate to represent the non-linear characteristics inherent in traffic prediction. However, the MLP model doesn't reflect local dependencies of traffic data and is prone to noise in traffic data. Convolutional Neural Networks (CNN) based model, on the other hand, can capture the local dependencies of traffic data and is less prone to disturbance in data. In this paper, we use temporal data and speed data collected on main roads in Seoul, South Korea to construct traffic prediction models. The speed data which are collected by every 5 minutes are provided by Ministry of Land, Infrastructure and Transport in South Korea. We construct the CNN based model and two MLP models which predict traffic speed and compare performance of the prediction models in this paper. The comparison results show that the CNN based model's prediction performance is higher than the prediction performance of the other two MLP models.

Traffic information prediction is one of the most essential studies for traffic research, operation and management. The successful prediction of traffic speed is increasingly significant for the benefits of both road users and traffic authorities. However, accurate prediction is challenging, due to the stochastic feature of traffic flow and shallow model structure. Furthermore, environmental factors, such as rainfall influence, should also be incorporated to improve accuracy. Inspired by deep learning, this paper investigates the performance of deep belief network (DBN) and long short‐term memory (LSTM) to conduct short‐term traffic speed prediction with the consideration of rainfall impact as a non‐traffic input. The deep learning models have the ability to learn complex features of traffic flow pattern under various rainfall conditions. To validate the performance of rainfall‐integrated DBN and LSTM, the traffic detector data from an arterial in Beijing are utilised for model training and testing. The experiment results indicate that with the combination input of speed and additional rainfall data, deep learning models have better prediction accuracy over other existing models, and also yields improvements over the models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time‐series characteristics of traffic speed data.

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

Short-term traffic speed prediction has become one of the most important parts of intelligent transportation systems (ITSs). In recent years, deep learning methods have demonstrated their superiority both in accuracy and efficiency. However, most of them only consider the temporal information, overlooking the spatial or some environmental factors, especially the different correlations between the target road and the surrounding roads. This paper proposes a traffic speed prediction approach based on temporal clustering and hierarchical attention (TCHA) to address the above issues. We apply temporal clustering to the target road to distinguish the traffic environment. Traffic data in each cluster have a similar distribution, which can help improve the prediction accuracy. A hierarchical attention-based mechanism is then used to extract the features at each time step. The encoder measures the importance of spatial features, and the decoder measures the temporal ones. The proposed method is evaluated over the data of a certain area in Hangzhou, and experiments have shown that this method can outperform the state of the art for traffic speed prediction.

Traffic prediction is an important part of building a smart city. Reasonable traffic prediction can help the relevant departments to make important decisions and help people to plan their travel routes. However, due to its complex spatial-temporal correlation has been a challenging task, and even though current research has progressed to some extent, it still generally focuses on modelling relationships between node pairs and between node history information, neglecting the analysis of node properties, leading to performance bottlenecks. To overcome these problems, we propose a dynamic spatial-temporal graph convolutional network (DSTGCN). Specifically, we design a dynamic graph generation module that collects information on geographical proximity and spatial heterogeneity between node pairs in advance and adaptively fuses the two types of information at each time step to generate a new dynamic graph. The dynamic graph module gives DSTGCN the ability to capture dynamic traffic information. In addition, we construct a graph convolution cycle module that captures local temporal dependencies on the basis of merging spatial relationships. It complements the dynamic graph module to jointly capture the spatial-temporal dependence of the traffic data. We validate the effectiveness of our model on two types of traffic prediction tasks, with DSTGCN outperforming the majority of baseline models.

The increasing complexity of urban transportation systems and the growing volume of vehicles have made traffic congestion a persistent challenge in modern cities. Efficient traffic flow prediction is essential for mitigating congestion, improving road safety, optimizing traffic signal control, and enhancing overall transportation efficiency. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the field of traffic management, offering sophisticated algorithms capable of modeling, analyzing, and predicting complex traffic patterns with high accuracy. The application of AI in traffic flow prediction leverages vast amounts of real-time and historical data to generate precise forecasts, supporting data-driven decision-making by urban planners and traffic control authorities. The prediction of traffic flow involves analyzing time-series data that exhibit nonlinear, dynamic, and often stochastic behavior. Traditional statistical models, such as autoregressive integrated moving average (ARIMA), have proven to be limited in handling the high dimensionality and variability inherent in traffic systems. In contrast, AI algorithms possess the capacity to learn and adapt from complex data inputs without the need for explicit programming, making them particularly suitable for traffic-related applications. AI algorithms used in traffic flow prediction can be broadly categorized into machine learning (ML) and deep learning (DL) approaches. Machine learning algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), decision trees, and random forests have demonstrated effectiveness in short-term traffic prediction tasks. These algorithms are capable of identifying hidden patterns in traffic data and adjusting to changes in traffic behavior over time. Ensemble methods, which combine the strengths of multiple learning models, further enhance prediction accuracy and robustness. Deep learning algorithms, a subfield of AI inspired by the human brain’s neural architecture, have shown exceptional performance in capturing spatial-temporal dependencies in traffic data. Recurrent neural networks (RNNs), particularly long short-term memory (LSTM) networks and gated recurrent units (GRUs), are widely used for their ability to process sequential data and retain information over extended time intervals. Convolutional neural networks (CNNs) are employed to extract spatial features from traffic sensor data or road network imagery. Hybrid models that integrate CNNs with RNNs have achieved high levels of predictive precision by simultaneously learning spatial and temporal correlations. In addition to supervised learning methods, unsupervised and reinforcement learning techniques are also applied in traffic flow prediction. Clustering algorithms, such as k-means and DBSCAN, assist in identifying traffic patterns, while reinforcement learning models optimize adaptive traffic signal control systems by learning optimal actions through environmental interaction. This study explores the different types of AI algorithms used in traffic flow prediction, examining their theoretical foundations, structural differences, and practical applications. It aims to evaluate the comparative advantages of various algorithms in addressing the challenges of real-time traffic prediction in increasingly complex transportation networks.

Analysis of traffic flow signals plays an important role in traffic prediction and management. As an intrinsic property, the singular point of a traffic flow signal labels a new nonsteady status. Therefore, detecting the singular point is an effective approach to determine the moment of traffic flow prediction. In this paper, an improved wavelet transform is proposed to detect singular points of real-time traffic flow signals. The number of detected singular points is output via the heuristic selection of multiple scales. Then, a weighted similarity measurement of historical traffic flow signals is utilized to predict the next singular point. The position of the next singular point decides the duration of prediction adaptively. The detected and predicted singular points are applied to dynamically update the unequal interval prediction of traffic flow. Furthermore, a Vasicek model is used to predict the traffic flow by minimizing the sum of the relative mean standard error (RMSE) between the traffic flow increment in the predicted interval and the sampled increments of previous intervals. A decomposition method is used to solve the unequal matrix problem. Based on the scenario and traffic flow imported from the real-world map, the simulation results show that the proposed algorithm outperforms existing approaches with high prediction accuracy and much lower computing cost.

Traffic speed prediction in the urban road network is an important and promising task of intelligent transportation systems. Precise traffic speed prediction can mitigate traffic congestion and improve road network utilization. This task is challenging because of the complexity of the spatiotemporal dependency of traffic data among road network. Existing approaches mainly focus on the whole road network and it may capture much redundant information and lead to high computational cost. In this paper, we propose a Key Path-Based Deep Learning Approach: Path-Based CNN-1D + GRU + CNN-2D (P-CGC), a novel deep learning model for traffic speed prediction. Specifically, we use EST-matching algorithm to match the float car data into the road network. Then we select several key paths and build the model for the loop detectors which are in the same key path. We introduce CNN-1D, GRU to extract the temporal dependency of the data, where CNN-1D is used to fuse the contextual information, and GRU is used to capture the features of the temporal dimension. Then we concatenate the output of all CNN-1D+GRU models and use CNN-2D to capture the spatial dependency of the data. Finally, a fully connected neural network is used to transform features into the prediction. We conduct extensive experiments on Zhangzhou real-world datasets, and the proposed approach achieves a good result.

Accurate traffic flow prediction is essential for the effective management of Intelligent Transportation Systems (ITS). However, traditional methods based on static graph structures often fail to address the complex and nonlinear spatiotemporal dependencies in evolving traffic conditions. To address this challenge, we propose a Dynamic Graph Convolutional Recurrent Network with Temporal Self‐Attention (DGCRN‐TSA), which integrates a temporal attention mechanism to jointly capture dynamic spatial topologies and long‐range temporal patterns. The model incorporates a graph generation module that adaptively learns time‐varying adjacency matrices from traffic signals and introduces a trend‐aware attention module enhanced by residual‐guided decomposition for distinguishing between normal and anomalous traffic behaviours. Experiments on real traffic datasets confirm that DGCRN‐TSA achieves superior performance in both short‐ and medium‐to‐long‐term forecasts. Notably, it reduces MAE by 19.4% on PeMS04 and improves MAPE by 12.2% on PeMS08. The model also ensures high prediction accuracy with strong computational efficiency and an inference speed comparable to AGCRN. DGCRN‐TSA offers an efficient and reliable solution for dynamic spatiotemporal modelling and large‐scale real‐time traffic prediction.

Multiple dynamic graph based traffic speed prediction method