Enhanced short-term traffic flow forecasting using a meteorological spatio-temporal transformer with multi-head attention and whale optimization.

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.

In modern intelligent transportation system, traffic control and traffic congestion management are main components of it. Real-time and accurate short-term traffic flow prediction is the precondition and key to realizing traffic control and traffic congestion management. In order to improve the accuracy of short-term traffic flow prediction, a combined model prediction method is proposed in this paper which is based on Xgboost and LightGBM algorithms. First, the short-term traffic flow data is preprocessed and features are sampled. Then, according to different characteristics, different prediction models are constructed by using Xgboost and LightGBM algorithms. Finally, these models are merged to generate the final model. Appling this model for prediction, the average travel time of the road can be obtained to predict the traffic flow and reflect road congestion. Experimental results show that the combined model has higher prediction accuracy than a single model, and it is an effective short-term traffic flow prediction method.

In recent years, China’s urbanization process has been accelerating, the number of motor vehicles has been increasing, and the problems of traffic congestion, traffic noise and environmental pollution have become increasingly prominent. The application of artificial intelligence system in the field of transportation provides a good idea to solve the above problems. Traffic flow prediction is to estimate the traffic flow in a period of time according to historical traffic data. This technology can provide decision-making basis for traffic guidance and path planning. In this paper, the deep learning theory of artificial intelligence technology is used to predict the short-term traffic flow, and the LSTM prediction model is constructed. On the basis of preprocessing the original data, through correlation analysis, compression matrix construction and other steps, a more accurate short-term traffic flow prediction is realized. According to the model, this paper also discriminates the actual road congestion, and the prediction results are basically consistent with the actual situation.

The accurate short-term traffic flow prediction can provide timely and accurate traffic condition information which can help one to make travel decision and mitigate the traffic jam. Deep learning (DL) provides a new paradigm for the analysis of big data generated by the urban daily traffic. In this paper, we propose a novel end-to-end deep learning architecture which consists of two modules. We combine convolution and LSTM to form a Conv-LSTM module which can extract the spatial-temporal information of the traffic flow information. Furthermore, a Bi-directional LSTM module is also adopted to analyze historical traffic flow data of the prediction point to get the traffic flow periodicity feature. The experimental results on the real dataset show that the proposed approach can achieve a better prediction accuracy compared with the existing approaches.

Accurate short-term traffic flow prediction is pivotal for intelligent transportation systems and smart city planning. This study presents a hybrid deep learning model Deep TrafficNet, which combines both Gated Recurrent Units (GRU) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks to predict the nature of the multi-junction traffic flow. The suggested model is demonstrated to have enhanced the extraction of temporal features and error in prediction is minimized with the help of massive real-world traffic data consisting of four urban intersections. To ensure the quality and stationarity of the data, the data were analysed by using the exploratory data analysis, z-score normalisation and Augmented Dickey-Fuller (ADF) test which yielded an overall RMSE value of 20.47, an improvement of 33% and 31% over LSTM and GRU baselines, respectively. The model was also suitable to model the junction-level variations with RMSEs of 31.43, 10.83, 13.51, and 17.79 in the four junctions. These results indicate that the model is efficient and scalable in its capacities to predict traffic effectively and which is important in adaptive traffic management of smart urban ecosystems.

Short-term traffic flow prediction can provide a basis for traffic management and support for travelers to make decisions. Accurate short-term traffic flow prediction also provides necessary conditions for the sustainable development of the traffic environment. Although the application of deep learning methods for traffic flow prediction has achieved good accuracy, the problem of combining multiple deep learning methods to improve the prediction accuracy of a single method still has a margin for in-depth research. In this article, a combined deep learning prediction (CDLP) model including two paralleled single deep learning models, CNN-LSTM-attention model and CNN-GRU-attention model, is established. In the model, a one-dimensional convolutional neural network (1DCNN) is used to extract traffic flow local trend features and RNN variants (LSTM and GRU) with attention mechanism are used to extract long temporal dependencies trend features. Moreover, a dynamic optimal weighted coefficient algorithm (DOWCA) is proposed to calculate the dynamic weights of CNN-LSTM-attention and CNN-GRU-attention with the goal of minimizing the sum of squared errors of the CDLP model. Then, the neuron number, loss function, optimization algorithm, and other parameters of the CDLP model are discussed and set through experiments. Finally, the training set and test set for the CDLP model are established through the processing of traffic flow data collected from the field. The CDLP model is trained and tested, and the prediction results of traffic flow are obtained and analyzed. It indicates that the CDLP model can fit the change trend of traffic flow very well and has better performance. Furthermore, under the same dataset, the results from the CDLP model are compared with baseline models. It is found that the CDLP model has higher prediction accuracy than baseline models.

Countermeasure Strategies against Traffic Congestion on Motorways in Japan

This paper is motivated by the following two related problems in complex networks: (i) control of cascading failures and (ii) mitigation of traffic congestion. Both problems are of significant recent interest as they address, respectively, the security of and efficient information transmission on complex networks. Taking into account typical features of load distribution and weights in real-world networks, we have discovered an optimal solution to both problems. In particular, we shall provide numerical evidence and theoretical analysis that, by choosing a proper weighting parameter, a maximum level of robustness against cascades and traffic congestion can be achieved, which practically rids the network of occurrences of the catastrophic dynamics.

Model predictive control policy design, solutions, and stability analysis for longitudinal vehicle control considering shockwave damping

Traffic congestion prediction is the premise to solve the problem of traffic congestion. Aiming at the problem that traffic volume was rarely considered in traffic congestion prediction based on spatio-temporal characteristics, this paper added two features of bus flow and time occupancy on the basis of temporal correlation and spatial correlation analysis of speed based on floating bus data. A BP neural network speed prediction model optimized by whale optimization algorithm (WOA) considering the temporal and spatial characteristics of bus flow was proposed, and the traffic state was divided into three levels by fuzzy theory. The results show that the speed prediction method based on temporal and spatial characteristics and bus flow characteristics proposed in this paper has good performance. Compared with the traditional BP neural network prediction results, the root mean square error and mean absolute error of WOA-BP neural network prediction model are reduced by 11.7% and 11.2% respectively, and the determination coefficient reaches 93.7%. The prediction accuracy of traffic congestion based on fuzzy theory is 90.06%, and the prediction accuracy of the model is higher.

Cardiac arrhythmias are the leading cause of death and pose a huge health and economic burden globally. Electrocardiography (ECG) is an effective technique for the diagnosis of cardiovascular diseases because of its noninvasive and cost-effective advantages. However, traditional ECG analysis relies heavily on the clinical experience of physicians, which can be challenging and time-consuming to produce valid diagnostic results. This work proposes a new hybrid deep learning model that combines convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) with multi-head attention (CBGM model). Specifically, the model consists of seven convolutional layers with varying filter sizes (4, 16, 32, and 64) and three pooling layers, respectively, while the BiGRU module includes two layers with 64 units each followed by multi-head attention (8-heads). The combination of CNN and BiGRU effectively captures spatio-temporal features of ECG signals, with multi-head attention comprehensively extracted global correlations among multiple segments of ECG signals. The validation in the MIT-BIH arrhythmia database achieved an accuracy of 99.41%, a precision of 99.15%, a specificity of 99.68%, and an F1-Score of 99.21%, indicating its robust performance across different evaluation metrics. Additionally, the model’s performance was evaluated on the PTB Diagnostic ECG Database, where it achieved an accuracy of 98.82%, demonstrating its generalization capability. Comparative analysis against previous methods revealed that our proposed CBGM model exhibits more higher performance in automatic classification of arrhythmia and can be helpful for assisting clinicians by enabling real-time detection of cardiac arrhythmias during routine ECG screenings.

Traffic speed prediction is an emerging paradigm for achieving a better transportation system in smart cities and improving the heavy traffic management in the intelligent transportation system (ITS). The accurate traffic speed prediction is affected by many contextual factors such as abnormal traffic conditions, traffic incidents, lane closures due to construction or events, and traffic congestion. To overcome these problems, we propose a new method named fuzzy optimized long short‐term memory (FOLSTM) neural network for long‐term traffic speed prediction. FOLSTM technique is a hybrid method composed of computational intelligence (CI), machine learning (ML), and metaheuristic techniques, capable of predicting the speed for macroscopic traffic key parameters. First, the proposed hybrid unsupervised learning method, agglomerated hierarchical K‐means (AHK) clustering, divides the input samples into a group of clusters. Second, based on parameters the Gaussian bell‐shaped fuzzy membership function calculates the degree of membership (high, low, and medium) for each cluster using Takagi‐Sugeno fuzzy rules. Finally, the whale optimization algorithm (WOA) is used in LSTM to optimize the parameters obtained by fuzzy rules and calculate the optimal weight value. FOLSTM evaluates the accurate traffic speed from the abnormal traffic data to overcome the nonlinear characteristics. Experimental results demonstrated that our proposed method outperforms the state‐of‐the‐art approaches in terms of metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

This study describes the result of six transportation demand management (TDM) implementations in three major traffic concentration periods of 2009-2010 with an expressway pre-registration and incentive scheme for electronic toll collection (ETC) vehicles in order to mitigate traffic congestion of the Tomei Expressway in Japan. The new TDM scheme offers an incentive to a limited number of pre-registered target travelers selected by drawings, from the viewpoint of reducing revenue loss, after confirming the eligibility of their travel as specified by the new TDM scheme with the ETC data. This scheme is considered more useful than the early applied TDM scheme with toll discount. The operator can control the total cost in the new TDM scheme, avoiding the large revenue loss incurred by the operator because of the toll discount in the early TDM scheme. The new scheme also has the advantage of easily conducting web surveys of the registrants' behavioural changes with regard to the TDM scheme. The characteristics of travelers' behavioural changes and the implementation effects of the TDM scheme are described.

Urban traffic congestion and carbon emissions pose significant challenges to the sustainable development of megacities. Traditional single-policy interventions often fail to simultaneously mitigate congestion and reduce emissions effectively. This study employs a system dynamics approach to construct a multidimensional dynamic model that analyzes the feedback mechanisms and dynamic interactions of policy variables within the urban traffic system. Furthermore, a TOPSIS multi-criteria decision-making framework is integrated to quantitatively evaluate the overall effectiveness of multiple policy combinations, exploring optimization pathways for achieving synergistic governance. Using Shanghai’s traffic system as a case study, simulation analyses under six policy scenarios reveal significant discrepancies in short- and long-term policy performance. Results demonstrate that traffic congestion, carbon emissions, and environmental pollution are tightly coupled, forming a non-coordinated feedback loop that challenges single-policy solutions. For example, the “two-license-plate restriction” policy reduces traffic congestion by 2.72%, carbon emissions by 10.37%, and pollution by 2.47% compared to the baseline scenario, achieving the highest TOPSIS score of 0.68. The “new energy vehicle promotion” policy significantly contributes to long-term emission reduction; however, its overall effectiveness score is relatively low at 0.5. These findings underscore the need for a systematic approach to urban traffic governance, providing actionable insights for balancing short-term effectiveness and long-term sustainability through dynamic policy integration.

Spatial distribution complexities of traffic congestion and bottlenecks in different network topologies