A hybrid deep learning framework that integrates Bidirectional Long Short-Term Memory and Gated Recurrent Unit networks with an attention mechanism within a federated learning paradigm is proposed, which enables decentralized model training across multiple data sources without requiring raw data sharing, thereby preserving privacy while maintaining predictive performance.
Problem of managing and controlling traffic congestion in Intelligent Transportation System (ITS). Classical, statistical and model-driven methods usually fail to take into account the nonlinear dynamic properties of congestion especially for that which concern abrupt transitions between free-flowing and congested states. Deep Learning (DL) has recently shown effective results as it is able to process large scale, high resolution data and elaborate on complex patterns that traditional methods tend to miss. To this end, a comprehensive survey is presented to investigate the most recent literature on DL-based methods for congestion prediction, detection and control, focusing on methodological advances, model diversity and performance improvements with respect to accuracy, scalability and computational complexity. At the same time, it highlights remaining gaps such as lack of robustness support in real-world scenarios, haphazard metrics interpretations and trade-offs between predictive accuracy and scalability. Through a critical review of the literature, this paper. In reviewing the available literature, this work underscores the potential of DL to improve congestion management and provides important pointers for future development in order to make it more applicable to sustainable and intelligent transportation systems.
Al Ani Mohammed Nsaif Mustafa, Mohd Murtadha Bin Mohamad, F. Muchtar· Acta Universitatis Sapientia...· 0 citations
This study presents a comprehensive review of machine learning (ML) and deep learning (DL) techniques for traffic flow prediction, identifying key methodological trends, performance strengths, and existing research gaps. The review systematically examines ML approaches such as K-means LSTM, KNN, and SVM, highlighting their effectiveness in short-term forecasting and feature-driven prediction scenarios. In addition, advanced DL architectures including CNN–LSTM, GRGCAN, and TS-RNN are analysed for their ability to capture complex spatial–temporal dependencies in traffic data, demonstrating superior adaptability and predictive accuracy in dynamic traffic environments. A key contribution of this study lies in its comparative synthesis of ML and DL models, revealing that hybrid and graph-based DL architectures consistently outperform traditional ML methods when handling large-scale, heterogeneous traffic datasets. The review further identifies critical limitations in existing studies, particularly challenges related to real-time deployment, limited integration of external factors such as weather and traffic incidents, and data quality constraints. Based on these findings, the study highlights the importance of incorporating multimodal transport data and external contextual information to improve prediction robustness. Overall, this review provides actionable insights for researchers and practitioners, supporting the development of more reliable and adaptive intelligent transportation systems to reduce urban congestion and improve traffic management.
Thabo Matue, A. A. Akinyelu, Mase Mokotsolane· International Journal of Dat...· 0 citations
FedTraffic, a hierarchical federated learning framework for traffic flow forecasting that integrates Edge–Fog–Cloud computing, hybrid deep learning, adaptive federated optimization, and Explainable Artificial Intelligence, is proposed.
Rapid urbanization, population growth, and the increasing number of vehicles have significantly intensified traffic congestion across metropolitan regions worldwide. Conventional traffic management systems are often inadequate for addressing the dynamic and nonlinear nature of urban transportation networks. Consequently, artificial intelligence (AI), particularly deep learning (DL), has emerged as a transformative approach for intelligent traffic flow prediction. Accurate traffic forecasting enables proactive traffic management, optimized route planning, reduced travel time, lower fuel consumption, and improved road safety, thereby contributing to the development of smart and sustainable cities. This systematic review critically examines recent advancements in deep learning-based traffic flow prediction models, emphasizing studies published between 2018 and 2026. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, this review synthesizes findings from high-quality journal articles, conference proceedings, and technical reports indexed in Scopus and Web of Science. The paper evaluates major deep learning architectures, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Networks (CNN), Graph Neural Networks (GNN), Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), Transformer-based architectures, and hybrid deep learning models. The review further analyzes their predictive performance, computational efficiency, scalability, interpretability, and real-world applicability in intelligent transportation systems. Existing challenges such as data heterogeneity, missing sensor data, privacy concerns, model explainability, computational cost, and deployment limitations are critically discussed. A conceptual research framework highlighting emerging technologies—including edge computing, Internet of Things (IoT), digital twins, federated learning, explainable AI, and large foundation models—is proposed to guide future research. The review contributes theoretically by synthesizing fragmented literature, technologically by identifying advanced predictive architectures, managerially by providing recommendations for transportation authorities, and sustainably by demonstrating how AI-driven traffic prediction supports greener and more efficient urban mobility. The findings indicate that although graph-based and transformer-based architectures currently achieve state-of-the-art predictive performance, integrating explainability, real-time adaptation, and privacy-preserving learning remains a significant research priority.
Keywords: Smart Traffic Prediction; Deep Learning; Intelligent Transportation Systems; Graph Neural Networks; Traffic Forecasting; Explainable Artificial Intelligence; Smart Cities
Dr. P. K. S. Bhadauria· International Journal of Cre...· 0 citations
Accurate network traffic forecasting is fundamental to Quality of Service enforcement, proactive congestion control, and dynamic resource allocation in modern backbone and software-defined networks. However, existing approaches often lack adaptability to non-stationary traffic patterns and fail to provide a consistent comparative evaluation across diverse models under unified experimental conditions. This paper presents an adaptive, data-driven framework that integrates Bidirectional LSTM (Bi-LSTM), LSTM, Gated Recurrent Units (GRU), Random Forest, XGBoost, Support Vector Regression (SVR), and classical ARIMA regressors for short- and medium-term traffic forecasting. The proposed architecture couples multi-scale temporal feature extraction with a feedback-driven online retraining loop, enabling continuous adaptation to distributional shifts. Extensive experiments are conducted on two publicly available datasets CAIDA Equinix backbone traces and the MAWI traffic archive comprising over 72 hours of flow-level measurements at one-minute resolution. Bi-LSTM achieves the lowest RMSE of 0.0287 Gbps and the highest $R^{2}=0.9714$, outperforming ARIMA by $\mathbf{7 5 . 2 \%}$ and vanilla LSTM by $\mathbf{8 . 0 \%}$. All results are confirmed via paired Diebold-Mariano (DM) tests and Student’s t-tests $(p \lt 0.01)$. System inference latency of 2.3 ms per batch satisfies real-time SDN control-plane requirements. Code and preprocessing scripts will be made publicly available to ensure full reproducibility.
E. Chithra, G. C. Bharathi, Sankara Rao et al.· International Conference on...· 0 citations
Traffic congestion in urban areas has become a major challenge due to rapid urbanization and the increasing number of vehicles, resulting in travel delays, environmental pollution, and reduced transportation efficiency. Existing traffic forecasting methods often struggle to capture complex temporal patterns and achieve consistent prediction performance in dynamic Internet of Vehicles (IoV) environments. This study proposes an Improved Dolphin Swarm‐optimized Dynamic Recurrent Neural Network (IDS‐DRNN), which integrates metaheuristic optimization with deep temporal learning for traffic flow prediction. The model is developed using a publicly available Kaggle Traffic Flow Monitoring Dataset comprising 4000 traffic records and 15 traffic‐related features, including vehicle density, speed, weather conditions, and network parameters. Min‐Max normalization is employed for data preprocessing, while principal component analysis (PCA) is used to reduce feature dimensionality and improve computational efficiency. The proposed model is implemented and evaluated using the Python environment. Experimental results indicate that IDS‐DRNN achieves an accuracy of 97.5%, precision of 96.5%, recall of 97.1%, RMSE of 1.01, and MAE of 0.48, demonstrating improved prediction performance compared with the baseline methods considered in this study. Although the Improved Dolphin Swarm optimization stage introduces additional computational complexity during model training, the trained model supports efficient inference for traffic flow prediction in IoV environments. Overall, the proposed IDS‐DRNN shows promising potential for supporting intelligent traffic management and reducing traffic congestion; however, further validation using larger and more diverse datasets is required to confirm its generalizability and reliability.
Maosheng Yan, Yihan Wang, Qingfeng Dong et al.· Concurrency and Computation· 0 citations