Jul 2026· 2026 International Conference on Emerging Trends in Information, Communication & Systems (ICETICS)· pp. 1-5· 0 citations· 14 references
Abstract
Accurate short-term traffic prediction is a critical component of intelligent transportation systems (ITS), yet it remains challenging due to nonlinear temporal dynamics, evolving spatial dependencies, and uncertainty in real-time urban traffic data. This paper proposes a novel uncertainty-aware deep ensemble spatiotemporal forecasting framework integrating Dynamic Graph Convolutional Networks (DGCN), Temporal Transformers, and CNN–LSTM hybrid models. A confidence-guided ensemble fusion strategy dynamically weights individual predictions using Bayesian uncertainty estimation. Experiments conducted on real-time Bhopal city traffic data demonstrate significant improvements over state-of-the-art baselines, achieving up to 90% performance gains during peak and abnormal traffic conditions.
Short-term traffic forecasting plays an important role in intelligent transportation systems, as applications such as route guidance, adaptive traffic signal control, emergency response, congestion mitigation, and logistics planning depend on accurate estimates of future traffic states. Recent spatio-temporal graph neural network models, particularly Diffusion Convolutional Recurrent Neural Network (DCRNN) and Spatio-Temporal Graph Convolutional Network (STGCN), have improved traffic prediction by representing road sensors as graph nodes and jointly learning spatial and temporal relationships. However, strong performance on clean benchmark datasets does not always guarantee reliability in real-world conditions, where sensor reading may be missing, noisy, or unavailable due to hardware faults or communication issues. This paper provides a robust focused comparative evaluation of seven traffic forecasting approaches: Persistence, Historical Average, ARIMA, Random Forest, LSTM, STGCN, and DCRNN. Experiments are conducted on the METR-LA and PEMS-BAY speed datasets using 5-minute data intervals, a 12-step historical input sequence, and a 12-step forecasting horizon. Under clean-data conditions, DCRNN achieves the best overall MAE on both datasets, with 3.548 mph on METR-LA and 1.905 mph on PEMS-BAY. However, when 40% random missing input corruption is introduced, STGCN shows greater robustness than DCRNN; for METR-LA, STGCN’s MAE increases by 27.0%, while DCRNN’s MAE increases by 34.5%. Under complete sensor-failure conditions, the model ranking changes further, with the LSTM baseline showing greater stability than both graph-based models on METR-LA. Graph ablation analysis also indicates that temporal modeling accounts for most of the forecast improvement, while the evaluated graph topology provides only limited additional benefits. These findings suggest that traffic forecasting models should be assessed not only by clean-data accuracy but also by their robustness under degraded sensing conditions before deployment in real intelligent transportation systems.
Shreya N. Desai, Kasim Ishaque Ghanchi, Ali Mehdi Mirza et al.· International journal of res...· 0 citations
The ability to forecast traffic conditions in urban environments is essential for intelligent transport systems because it provides proactive congestion management, traffic control and informed urban mobility planning. However, due to the extreme spatial and temporal volatility of traffic flow patterns, conventional statistical, machine learning, and sequence-based deep learning approaches either fail to account for the spatial relationships between highway segments or fail to sufficiently model long-range temporal dynamics. To address these gaps, the present study uses a Spatial-Temporal Graph Neural Network (STGNN) framework that can learn a combination of spatial and temporal relationships in road networks and changing time-varying patterns in traffic flow. The model has a graph-based architecture where graph-convolutional layers are combined with gated recurrent units and transformer-based attention units, thus creating a hybrid architecture that is capable of multi-scale spatio-temporal dependencies. The METR-LA dataset was used in experiments, and it was observed that STGNN had smaller Mean Absolute Percentage Error(MAPE), Mean Absolute Error(MAE), and Root Mean Squared Error(RMSE) at 15, 30, and 60 minute horizons of prediction than the baseline and the implemented models: Sequence to Sequence (Seq2Seq) and Temporal Graph Convolutional Network (T-GCN). The model achieved the best results for the 15-minute interval with an MAE of 2.71, an RMSE of 5.17, and a MAPE of 7.08. The results imply that adaptive spatial learning, together with the temporal sequence modeling, can produce much better forecasting stability, which underlines the potential STGNN-based traffic prediction systems have to contribute to real-time traffic control.
Traffic congestion is a growing challenge in urban environments, driven by increasing population and vehicle density, leading to significant economic and societal impacts. Accurate traffic forecasting is a key component of Cooperative Intelligent Transportation Systems (C-ITS), enabling proactive traffic management strategies such as adaptive signal control and dynamic routing. However, existing approaches often struggle to capture spatial dependencies in road networks and long-range temporal dynamics in traffic data. This paper proposes TETRA, a hybrid spatio-temporal traffic forecasting model that integrates Graph Convolutional Networks (GCNs) with Extended Long Short-Term Memory (xLSTM). By incorporating matrix-based memory and memory mixing, xLSTM enables the model to capture complex multi-timescale temporal patterns, including congestion propagation and delayed recovery dynamics, which are not well represented by conventional recurrent models. The proposed approach is evaluated on a real-world urban traffic dataset and the widely used METR-LA benchmark. Experimental results show that TETRA outperforms or matches established baseline models representative of the main spatio-temporal paradigms, with the most pronounced gains at medium- and long-term horizons, achieving up to 13.0% lower MAE, 20.0% lower RMSE, and 6.0% higher
$$R^2$$
on a real-world dataset relative to the strongest investigated baseline at each horizon. Statistical analysis confirms that these improvements are robust across prediction horizons. Additional evaluations, including ablation and sensitivity analyses, demonstrate the effectiveness and scalability of the proposed model.
Norman Bereczki, Vilmos Simon· International Journal of Int...· 0 citations
Efficient traffic-state prediction at urban intersections is a critical component of intelligent transportation systems(ITS), as traffic conditions are influenced by dynamic factors such as traffic demand variability, infrastructure constraints, and operational traffic-control policies. This study proposes a deep-learning-based approach for short-term traffic-state classification using real-world traffic data collected during 2022 at the Alésia intersection in Paris. The objective is to classify traffic conditions into five operational states: Unknown, Flowing, Pre-saturated, Saturated, and Blocked. To investigate the impact of temporal modeling on traffic-state recognition, four deep learning architectures were evaluated under identical experimental conditions: Artificial Neural Networks (ANN), Simple Recurrent Neural Networks (RNN),Long Short-Term Memory networks (LSTM), and Gated Recurrent Units (GRU). Considering the highly imbalanced nature of the dataset, model performance was assessed using complementary metrics including Accuracy, Precision, Recall, F1-score, Macro-F1 score, and Balanced Accuracy. Experimental results demonstrate that recurrent architectures substantially outperform the ANN baseline, highlighting the importance of temporal dependencies in traffic-state classification. While the conventional RNN achieves high overall accuracy, its performance on minority traffic states remains limited. Among the evaluated models, the LSTM achieves the highest Balanced Accuracy (70.91%), indicating superior recognition of underrepresented traffic conditions. The GRU attains the highest overall F1-score (0.9256) and Macro-F1 score (0.497), while maintaining competitive classification accuracy (91.01%), providing the most favorable trade-off between global predictive performance and balanced class-wise recognition.The analysis of learning curves, classification reports, and confusion matrices further confirms the effectiveness of gated recurrent architectures for handling highly imbalanced multiclass traffic-state classification problems. These findings provide practical insights for the deployment of intelligent traffic-monitoring systems capable of supporting real-time traffic management and decision-making in urban environments.
Chaymae Chouiekh, Ali Yahyaouy, M. A. Sabri et al.· Vehicles· 0 citations
Intelligent Transportation Systems (ITS) are undergoing a paradigm shift driven by the unprecedented volume of multi-modal data and the necessity for highly accurate, real-time predictive analytics. Traditional machine learning and deep learning architectures, while effective for localized tasks, often struggle with spatial-temporal distribution shifts, cross-city generalization, and the integration of heterogeneous data sources such as traffic cameras, GPS trajectories, weather reports, and textual incident logs. This paper investigates the application of Foundation Models (FMs) large-scale architectures pre-trained on massive datasets and fine-tuned for downstream tasks as the core engine for next-generation ITS predictive analytics. The article presents a generic framework which exploits the zero-shot, few-shot and multi-modal capabilities of foundation models to forecast traffic flow, predict traffic incidents and improve public transit schedules. This study uses large-scale comparisons and empirical simulations to evaluate the structural benefits, integration techniques, and performance trade-offs of FMs against common deep learning frameworks. The results show that foundation model-based methods achieve better generalization on unseen urban networks and high robustness towards the noisy or missing sensor data. Lastly, we identify some of the principal two-sided challenges including computational overhead, latency constraints in edge deployment and privacy protection, also discuss a few strategies for addressing these issues and direction towards new research and deployable practices within smart city infrastructures.
W. T L· International Journal of Com...· 0 citations
Aiming at the problem that single-modal features are difficult to depict the complex spatiotemporal evolution law in urban traffic risk prediction, a multimodal spatiotemporal deep learning model fusing Multi-view Graph Convolutional Network (GCN), Transformer and Temporal Convolutional Network (TCN) is proposed to realize binary traffic risk prediction at the 10×10 grid level. Based on the traffic dataset of Area C in New York City (NYC), the study integrates grid time series, static features and multi-type adjacency matrix data. Strategies such as outlier processing, dynamic threshold binarization and feature normalization are adopted to solve the problems of data quality and imbalance between positive and negative samples. Meanwhile, gradient clipping, weighted loss and early stopping strategies are combined to ensure the stability of model training. Experimental results show that the model achieves an F1 score of 0.745, an AUC-ROC of 0.798 and an AUC-PR of 0.756 on the test set. It can effectively capture the spatial correlation and temporal dependence features of traffic risks, maintain good prediction performance in the unbalanced data scenario, and meet the actual business needs of urban traffic risk prediction.
Yusen Liu· Frontiers in Computing and I...· 0 citations