Deep spatio-temporal 3D densenet with multiscale ConvLSTM-Resnet network for citywide traffic flow forecasting

As one of the most widely used applications of the Internet of Things (IoT), intelligent transportation system (ITS) is of great significance for urban traffic planning, traffic control, and traffic guidance. However, widespread traffic congestion occurs with the increased number of vehicles. The traffic flow prediction is a good idea for traffic congestion. Therefore, many schemes have been proposed for accurate and real-time traffic flow prediction, but there still exist many issues, including low accuracy, weak adaptability and inferior real-time. Meanwhile, the complex spatial and temporal dependencies in traffic flow are still challenging. To address the above issues, we propose a novel spatial-temporal Chebyshev graph neural network model (ST-ChebNet) for traffic flow prediction to capture the spatial-temporal features, which can ensure accurate traffic flow prediction. Concretely, we first add a fully connected layer to fuse the features of traffic data into a new feature to generate a matrix, and then the long short-term memory (LSTM) model is adopted to learn traffic state changes for capturing the temporal dependencies. Then, we use the Chebyshev graph neural network (ChebNet) to learn the complex topological structures in the traffic network for capturing the spatial dependencies. Eventually, the spatial features and the temporal features are fused to guarantee the traffic flow prediction. The experiments show that ST-ChebNet can make accurate and real-time traffic flow prediction compared with other eight baseline methods on real-world traffic data sets PeMS.

In metropolitan areas, common traffic issues include traffic congestion, traffic accidents, air pollution, and energy consumption occur. To resolve this issues, Intelligent Transportation Systems (ITS) have been evolved by many researchers. One of the important sub-systems in the development of ITS is a Traffic Management System (TMS) which attempts to reduce a traffic congestion. In fact, TMS itself relies on the estimation of traffic flow, therefore providing such an accurate traffic flow prediction is needed. For this reason, we aim to provide an accurate traffic flow prediction to facilitate this system. In this works, a Supervised Deep Learning Based Traffic Flow Prediction (SDLTFP) was proposed which is a type of fully-connected deep neural network (FC-DNN). Timely prediction is also a major issue in guaranteeing reliable traffic flow prediction. However, training a deep network could be time-consuming, and overfitting is might be happening, especially when feeding small data into the deep architecture. The network is learned perfectly during the training, but in testing with the new data, it could fail to generalize the model. We adopt the Batch Normalization (BN) and Dropout techniques to help the network training. SGD and momentum are carried out to update the weight. We then take advantage of open data as historical traffic data which are then used to predict future traffic flow with the proposed method and model above. Experiments show that the Mean Absolute Percentage Error (MAPE) for our traffic flow prediction is within 5 % using sample data and between 15% to 20% using out of the sample data. Training a deep network faster with BN and Dropout reduces the overfitting.

Research on spatio-temporal network prediction model of parallel–series traffic flow based on Transformer and GCAT

Traffic flow prediction is an important part of intelligent transportation system (ITS). Accurate traffic flow prediction information can provide reliable reference for traffic management decision-makers, effectively reduce traffic congestion, reduce vehicle exhaust pollution, save energy and facilitate the travel of the people. Most of the existing traffic flow prediction models simplify the traffic flow change process into a linear and stable process and ignore the influence of weather conditions on traffic flow, which will lead to large prediction deviation. In order to improve the accuracy of traffic flow prediction, this paper proposes an ensemble learning method based on ET and AdaBoost for fusing traffic and meteorological data under the non-stationary environment to predict the changes of traffic flow. The experiment is based on real traffic and meteorological data, and the results show that the proposed ensemble method is superior to the baseline methods.

Short-term traffic flow prediction plays an important role in intelligent transportation system. Numerous researchers have paid much attention to it in the past decades. However, the performance of traditional traffic flow prediction methods is not satisfactory, for those methods cannot describe the complicated nonlinearity and uncertainty of the traffic flow precisely. Neural networks were used to deal with the issues, but most of them failed to capture the deep features of traffic flow and be sensitive enough to the time-aware traffic flow data. In this paper, we propose a deep bi-directional long short-term memory (DBL) model by introducing long short-term memory (LSTM) recurrent neural network, residual connections, deeply hierarchical networks and bi-directional traffic flow. The proposed model is able to capture the deep features of traffic flow and take full advantage of time-aware traffic flow data. Additionally, we introduce the DBL model, regression layer and dropout training method into a traffic flow prediction architecture. We evaluate the prediction architecture on the dataset from Caltrans Performance Measurement System (PeMS). The experiment results demonstrate that the proposed model for short-term traffic flow prediction obtains high accuracy and generalizes well compared with other models.

Accurate traffic flow prediction is crucial for improving transportation efficiency. To improve the accuracy of traffic flow prediction, we developed a traffic flow prediction framework—namely, traffic flow multicomponent network—that appropriately processes the noise, volatility, and nonlinearity in traffic flow data. This framework comprises three components: a factor selection component, traffic flow decomposition component, and traffic flow prediction component. The factor selection component considers the dynamic effects of weather‐related, environmental, and spatiotemporal factors on traffic flow; it then extracts and analyzes factors exhibiting strong correlations with traffic flow. The traffic flow decomposition component optimizes the parameters of variational mode decomposition on the basis of the envelope entropy by using the sparrow search algorithm; it then transforms traffic flow into multiple intrinsic mode functions to enable accurate traffic flow prediction. Finally, the traffic flow prediction component constructs dynamic feature matrices by using a bidirectional gated recurrent unit model to identify relationships within the data. Moreover, it uses an attention mechanism to assign different weights to different features on the basis of the importance of these features to traffic flow prediction, thereby enabling the efficient processing of a large volume of data. The performance of the proposed framework was examined in experiments conducted on large volumes of traffic flow data with different time granularities. The results indicated that the proposed framework achieved high prediction accuracy and stability for various time granularities, data samples, dataset sizes, and noise conditions. Moreover, it generally outperformed existing traffic flow prediction models under all experimental conditions.

Recent development in ITS (intelligent transportation systems) methods and technologies has moved traffic operating systems from passive to proactive control and management, where real-time and accurate traffic flow information is critical to actual implementation. So far many algorithms have been proposed for traffic network flow forecasting, but problems in accuracy and timeliness still remain to be the major obstacle for their successful applications. For example, presumed human travel habit and vehicle turning probabilities at intersections have greatly limited the use of dynamic assignment algorithm. In order to improve the forecasting and real-time responsiveness, a new algorithm based on data mining which can do association rules mining and association analysis is proposed here for predicting traffic network flow. Simulation results using Corsim 5.0 have demonstrated effectiveness of the new algorithm in both accuracy and timeliness.

With the acceleration of urbanization and the continuous growth of transportation demand, traffic flow prediction has become a key research issue in ITS (Intelligent Transportation System). In this paper, a traffic flow prediction model based on VMD-ARO-BiLSTM is proposed, which can make full use of the spatio-temporal characteristics of traffic data to achieve high-precision traffic flow prediction. First, the traffic flow data are input into VMD (Variational Mode Decomposition) for data reconstruction. Then, the optimal parameter values of BiLSTM (Bi-directional Long Short-Term Memory) are solved using ARO (Artificial Rabbits Optimization) to complete the optimization of BiLSTM. Finally, the reconstructed data are input into BiLSTM to realize the accurate prediction of traffic flow. To verify the model performance, we conducted experiments using traffic flow data from different time periods. The experimental results show that on weekdays, the combined VMD-ARO-BiLSTM prediction model decreases the RMSE (Root Mean Square Error) by 47.2% and the MAE (Mean Absolute Error) by 44.6% compared to BiLSTM; on weekends, compared to BiLSTM, the RMSE decreases by 26.1% and MAE decreases by 23.4%, reflecting the strong robustness and applicability of this model, which has certain application value.

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 flow prediction remains a significant challenge in intelligent transportation systems. To enhance prediction accuracy, a hybrid model is proposed that integrates an improved Variational Mode Decomposition (VMD), a Residual Spatio-Temporal Graph Convolutional Network (RSTGCN), a Long-term Time Series Informer Network (LTSIN), and an iterative error compensation strategy. This approach effectively addresses the non-stationarity, spatial correlations, and temporal dependencies inherent in traffic data. First, the VMD is optimized using a Crested Porcupine Optimizer algorithm to decompose traffic flow time series into intrinsic mode functions (IMFs), each capturing different traffic patterns. Next, these IMFs are then input into the LTSIN and RSTGCN modules. The LTSIN models long-term temporal dependencies, while the RSTGCN captures short-term temporal and spatial relationships. Residual connectivity within the RSTGCN allows the model to retain node features and aggregate information from neighboring nodes, mitigating the over-smoothing issue typically seen in graph convolutional networks. Lastly, an iterative error correction mechanism is applied, where the IMF-derived predictions are refined and reconstructed to yield the final forecast. The effectiveness of the proposed model is demonstrated by extensive experiments, including ablation experiments, baseline comparisons, and multi-step forecasting experiments. Compared to existing models such as GCN and Informer, the proposed method reduces MAE by 8.78 and 6.79, and MAPE by 6.48% and 5.52%, respectively. These results indicate that the proposed model achieves superior prediction accuracy and can be effectively applied to traffic flow prediction tasks.

Accurate traffic flow forecasting is a crucial need for Intelligent Transportation Systems (ITSs). This supports dynamic and proactive traffic control management. The challenging part lies in reducing the forecast error rate. There was limited success in the previous attempts put forth to develop traffic flow forecasting systems. In this work, the MIDAS Site—UK Highways data is used to predict the traffic flow using the hybrid CNN-LSTM model. The data is preprocessed using Z-Score Normalization in order to scale the data below and above the standard deviation. The features from the preprocessed data are learnt using the CNN model and with these extracted features as input, the LSTM network forecasts the traffic flow. The CNN model, LSTM model and hybrid CNN-LSTM model are trained with the preprocessed data. The trained models are tested for estimating the traffic flow. The results convey that the hybrid CNN-LSTM model proposed forecasts the traffic flow with a reduced error rate.KeywordsTraffic flow forecastingConvolutional Neural Network (CNN)Long Short-Term Memory (LSTM)Hybrid CNN-LSTM modelIntelligent transportation system

Accurate traffic flow prediction plays a vital role in intelligent transportation systems, helping traffic management departments maintain stable traffic order, reduce traffic congestion, and improve road safety. Existing prediction methods focus on dynamic modeling of the spatiotemporal dependencies of traffic flow, capturing the periodicity and spatial heterogeneity in traffic data. However, they still suffer from a lack of focus on the important local information in long-term predictions, leading to overly smooth results that fail to effectively capture sudden changes in traffic patterns. To address these limitations, we propose the sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network (sAMDGCN) model. Specifically, we extend sLSTM and introduce temporal trend-aware multi-head attention to jointly capture the complex temporal dependencies. We propose a multi-head dynamic graph convolutional network to capture a wider range of dynamic spatial dependencies. To validate the effectiveness of sAMDGCN, we perform extensive experiments on four real-world traffic flow datasets. Experimental results show that our proposed sAMDGCN model outperforms the advanced baseline methods in long-term traffic flow prediction tasks, demonstrating its superior performance in capturing complex and dynamic traffic patterns.

Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting

To address the issue of spatiotemporal illusion in short-term traffic flow prediction and deeply explore the underlying short-term traffic flow network characteristics, a traffic flow prediction model that combines long-term spatiotemporal heterogeneity with short-term spatiotemporal features is proposed. In the long-term spatiotemporal branch, the Transformer structure is employed, and a self-supervised masking mechanism is utilized to pretrain the heterogeneity in long-term temporal and spatial dimensions separately. Additionally, a spatiotemporal adaptive module is designed, which adapts to and guides short-term traffic flow prediction across time series and traffic flow networks. In the short-term spatiotemporal branch, a recurrent neural ordinary differential equation (ODE) module is devised. This module is capable of continuously and dynamically adjusting short-term spatiotemporal features, better capturing and exploring potential short-term spatiotemporal characteristics. Through multiple cycles, this module gradually and accurately extracts and compresses road network features, integrates the adapted spatiotemporal heterogeneity, and reconstructs future short-term traffic flows in the decoder. Experiments are conducted on four traffic flow and two traffic speed datasets, showing that compared to traditional time series models, the proposed model’s prediction accuracy indicators have relatively improved by 45.09%, 39.14%, and 0.47% on average; compared to recurrent neural network (RNN) series models, the improvements are 18.91%, 15.77%, and 0.18% on average; compared to graph convolution series models, the improvements are 21.31%, 16.65%, and 0.21% on average; and compared to Transformer series models, the improvements are 6.57%, 6.23%, and 0.05% on average. The model’s general applicability and good performance in transportation speed scenarios were verified through a multi-step experiment conducted on the transportation speed dataset.

Traffic flow forecasting is an important issue for the application of intelligent transportation systems (ITS). How to improve the traffic flow forecasting precision is a crucial problem. Traffic models in different time sections have great differences. The forecasting precision could be improved if the traffic flow forecasting models were built on different time sections respectively. Traffic flow forecasting usually is real-time and too many forecasting variables will reduce the real-time performance. So the selection of the most informative forecasting variable combination is significant. It can save computation cost and improve forecasting precision. In this paper, information bottleneck theory based on extended entropy is used to partition traffic flow of a day into different time sections. Corresponding to each time section, feature selection based on mutual information is generalized to regression problems and is used to select the most informative variable combination. Selected variables are input to support vector machines (SVM) for traffic flow forecasting. Bayesian inference is used to determine the kernel parameters of SVM. The efficiency of the method is illustrated through analyzing the traffic data of Jinan urban transportation.