TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting

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.

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.

Urban traffic flow prediction plays an important role in traffic flow control and urban safety risk prevention and control. Timely and accurate traffic flow prediction can provide guidance for traffic, relieve urban traffic travel pressure and reduce the frequency of accidents. Due to the randomness and fast changing speed of urban dynamic traffic data flow, most of the existing prediction methods lack the ability to model the dynamic temporal and spatial correlation of traffic data, so they cannot produce satisfactory prediction results. A spatio-temporal convolution network (ST-CNN) is proposed to solve the traffic flow prediction problem. The model consists of two parts: 1) a convolution block used to extract spatial features; 2) a block of time used to characterize time. Data has been fully mined through two modules to output the prediction results of spatio-temporal characteristics, and at the same time, skip connection (direct connection) has been made between the two modules to avoid the problem of gradient explosion. The experimental results on two data sets show that ST-CNN is better than the baseline model.

Traffic flow forecasting is one of the key issues in smart traffic systems. The process of traffic flow changing involves a high degree of nonlinearity and randomness, environmental interference and measurement noise, which brings difficulties to accurate traffic flow prediction. Aiming at improving the accuracy of short-term traffic flow prediction, this paper proposes a method called Basis Prediction method. A raw traffic flow series can be deemed as a summation of a basis series that indicates the changeable trend of the traffic flow and a deviation series that represents the random interference information involved in the flow. The basis series comprises mainly low-frequency signals and the deviation series is composed of some high-frequency signals. Based on an appropriate extraction of the basis series, prediction merely of the basis series brings more precise prediction of the raw traffic flow. This paper suggests adopting wavelet decomposition to obtain the basis series and the deviation series from the raw traffic flow. To predict the basis series effectively, two algorithms, local weighted partial least squares (LW-PLS) and Kalman filtering, are adopted separately and a comparison between them is also provided. In this paper, real data of traffic flow of Xinbei city in Taiwan was collected and used for validation of the proposed basis prediction method. The results show that the use of that proposed method improves the accuracy of short-term traffic flow prediction by about 2% on average.

Traffic flow prediction can guide the rational layout of land use. Accurate traffic flow prediction can provide an important basis for urban expansion planning. This paper introduces a personalized lightweight federated learning framework (PLFL) for traffic flow prediction. This framework has been improved and enhanced to better accommodate traffic flow data. It is capable of collaboratively training a unified global traffic flow prediction model without compromising the privacy of individual datasets. Specifically, a spatiotemporal fusion graph convolutional network (MGTGCN) is established as the initial model for federated learning. Subsequently, a shared parameter mechanism of federated learning is employed for model training. Customized weights are allocated to each client model based on their data features to enhance personalization during this process. In order to improve the communication efficiency of federated learning, dynamic model pruning (DMP) is introduced on the client side to reduce the number of parameters that need to be communicated. Finally, the PLFL framework proposed in this paper is experimentally validated using LPR data from Changsha city. The results demonstrate that the framework can still achieve favorable prediction outcomes even when certain clients lack data. Moreover, the communication efficiency of federated learning under this framework has been enhanced while preserving the distinct characteristics of each client, without significant interference from other clients.

With rapid economic growth and urbanization, the accelerated increase in car ownership has brought massive pressure on urban traffic, and accurate traffic flow prediction information can provide an important basis for urban traffic dynamic planning. The existing methods have problems such as low efficiency, large error, and inability to adapt to short‐term traffic changes. To solve the above problems, the CEEMDAN‐SE‐GWO‐LSTM method was proposed in this paper. First, the traffic flow data is processed for outliers and missing values. The Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method is used to decompose the traffic flow data, and sample entropy (SE) is used to reconstruct the subsequence, which is used to improve the quality of the input data. Then, the Grey Wolf Optimizer (GWO) is used to optimize the parameters of the long‐short‐term memory (LSTM) in order to improve the prediction accuracy and prevent the model from falling into a local optimum. Three models are used to compare with the ensemble model proposed in this paper, including back propagation neural network (BPNN), LSTM, and long‐short‐term memory optimized by Grey Wolf Optimizer (GWO‐LSTM). Root mean square error (RMSE) is reduced by 40.9% to 66.7%; R2 score is improved by 1.5% to 7.1%. The experimental results show that CEEMDAN‐SE‐GWO‐LSTM has a higher prediction accuracy than the existing traffic flow prediction models. Finally, this paper uses the model prediction error to establish an interval prediction model based on the kernel density estimation theory, which enhances the generalization of the model and the practical application value.

Traffic flow has the characteristics of randomness, nonlinearity and periodicity. Using deep learning as the method of traffic flow prediction can make full use of traffic flow characteristics for prediction. In this paper, a recurrent neural network-LSTM (Long Short-Term Memory) model and its variant GRU (Gated Recurrent Units) are used to solve the traffic flow prediction problem. According to the road traffic information collected by the automatic measurement station (LAM) of the Dutch traffic management department, the vehicle traffic flow data has been predicted every five minutes. It’s verified that the GRU traffic flow prediction model performs well by comparing the prediction accuracy of LSTM and GRU.

A Single traffic flow prediction method has weak applicability for short-time traffic flow prediction. In order to adapt to the needs for traffic guidance and signal control, a short-time traffic flow RBF neural network model combination prediction method based on wavelet de-nosing processing is put forward. First, the traffic flow data are decomposed and reconstructed by using the wavelet transform technique. Then Under the intensive analysis the characteristics of short-time traffic flow, the low frequency outline signal and high frequency detail signal are fitted respectively by using two different RBF neural network models, and particle swarm optimization (PSO) algorithm is proposed to train RBF neural network. The confirmation analysis is carried on with traffic flow data from typical roads in some city urban districts. The results show that the precision of combination prediction method is significantly improved.

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.

Traffic flow has the characteristics of complex spatial dependence and temporal dependence. Deep learning as a traffic flow prediction method can make full use of the temporal and spatial characteristics of traffic flow. In this paper, the road network is abstracted into a graph structure, the size of the graph structure is dynamically changed, and the graph convolutional neural network (GCN) and the long short term memory network (LSTM) are used to capture the temporal and spatial characteristics of traffic flow to solve the traffic flow prediction problem. Based on the data of vehicle speed in California bay area, the experiment is divided into three prediction scales. The effectiveness of the traffic flow prediction model is verified by experimental comparison.

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.

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.

As a cornerstone of intelligent transportation systems, traffic flow prediction has garnered extensive research attention. However, traffic flow data exhibits pronounced spatio-temporal dynamics, rendering accurate traffic flow prediction a challenging endeavor. Existing methodologies compartmentalize the capture of temporal and spatial dependencies through distinct modules, overlooking latent spatio-temporal heterogeneity within traffic data. Furthermore, they often solely consider spatio-temporal correlations between adjacent historical time steps, neglecting the extraction of temporal dependencies across different time intervals. To address these issues, we propose a novel Multi-scale Fusion Dynamic Graph Neural Network (MFDGNN). MFDGNN employs Temporal Convolutional Networks (TCNs) to generate time series on multiple scales, subsequently extracting spatio-temporal features from these sequences to construct mutually independent fusion graphs. By leveraging fusion graphs to extract features from time series on multiple scales, our model adeptly captures spatio-temporal dependencies of traffic nodes across various time dimensions, thereby achieving enhanced precision in traffic flow prediction. Experimental results conducted on four publicly available datasets demonstrate the superiority of our model compared to other baseline approaches.

The prediction of abnormal traffic flows has always been a primary concern in traffic management. If the management unit can predict the occurrence of abnormalities, it can manage and control transportation in advance in order to avoid abnormal traffic flows and enhance the service quality. While previous researchers generally predicted abnormal conditions in traffic flows by means of a single time series prediction model, such methods might result in inaccuracy in the prediction of abnormal traffic flows in some areas. As a result, in terms of practicality, the traditional methods fail to produce satisfactory results. Moreover, with the traditional methods, researchers often find it difficult to obtain the best time-delay item in the model and can only do so by using the trial-and-error method, which is nevertheless cost-prohibitive. In order to solve this problem, in this study, we predicted abnormal traffic flows by using the Ensembling-mRBF-LSTM framework, which consists of three new concepts: (1) introducing the concept of ensembling learning to the target issue and integrating the results produced by multiple existing prediction methods into the prediction of abnormalities, (2) devising the concept of mRBF-LSTM to select the prediction methods applicable to the prediction of abnormalities in this study from the existing methods and to decide on the applicable time-delay item for each existing prediction method, and (3) predicting abnormalities by using only the existing methods selected via mRBF-LSTM. With the aforementioned three major concepts, in this study, we sought to vastly improve the existing method for abnormal traffic flow prediction. Lastly, this study provided the traffic flow data of Taipei Mass Rapid Transit (MRT) in Taiwan to verify the effectiveness of the proposed method.

Accurate short-term traffic flow prediction is the foundation of the efficient and proactive management of freeway networks, especially on the abnormal traffic states. The relationship between traffic flow on the current section and the upstream stations can be used for predicting short-term traffic flow. In this paper, we reveal this relationship by the traffic flow structure pattern. The structure pattern can be drawn from real freeway toll data and a few video detective cameras on the freeway segments. Based on the stability pattern, a new traffic flow prediction algorithm has been proposed. Experimental based on real data showed that the prediction method based on structure pattern is an effective approach for traffic flow prediction, especially on the abnormal traffic state.