Optimal deep neural network based road traffic management system for Internet of Things based smart city environment.

Almejalli, KA · 2026 · PubMed Central

DOI: 10.1038/s41598-026-42542-8

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the challenge of managing urban traffic congestion and improving safety in Internet of Things (IoT)-enabled smart cities. Motivated by rapid urbanization and the limitations of existing models—which often suffer from low performance, lack of robustness, or reliance on static assumptions—the study proposes a novel decision support system for road traffic management. The primary goal is to leverage real-time data from IoT sensors and connected vehicles to optimize traffic flow, reduce congestion, and enhance operational efficacy through advanced deep learning techniques. The authors introduce the Hybrid Feature Selection and Deep Neural Network for Decision Support Systems in Road Traffic Management (HFSDNN-DSSRTM) model. The methodology consists of three main stages. First, data pre-processing is conducted at dual levels: missing values are handled using mean imputation, and features are standardized using Min-Max normalization to ensure input consistency and improve model convergence. Second, a hybrid feature selection approach combines filter, wrapper, and embedded methods to identify the most valuable features for classification while mitigating computational overhead. Finally, the model employs a Temporal Convolutional Network with an Attention Mechanism (TCN-AM) for classification. This architecture is designed to capture both short- and long-term temporal dependencies in traffic data, utilizing attention-based feature weighting to enhance prediction accuracy. The proposed HFSDNN-DSSRTM model was evaluated using the Smart Traffic Management dataset. The experimental results demonstrate that the model achieves a superior accuracy of 98.75%, outperforming existing methods reviewed in the literature. The integration of TCN-AM allows for efficient handling of dynamic traffic patterns, while the hybrid feature selection process ensures that only relevant data contributes to the classification task, thereby improving both performance and efficiency. The significance of this work lies in its contribution to intelligent transportation systems by providing a robust, data-driven framework for real-time traffic management. By effectively combining IoT data collection with advanced deep learning architectures, the model offers a scalable solution for reducing urban congestion and improving road safety. The study highlights the potential of adaptive, interpretable, and data-efficient models in addressing the complexities of modern smart city infrastructure, offering a significant improvement over conventional traffic prediction and management systems.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• telematics crash prediction