Urbanization and increased vehicle numbers exacerbate traffic congestion, posing significant challenges to sustainable urban mobility. Intelligent Transportation Systems (ITS) combined with Artificial Intelligence (AI) provide innovative solutions. Existing traffic management strategies are limited by their static nature, resulting in suboptimal traffic flow and elevated pollution levels due to their inability to adapt to urban dynamics. Traditional methods, reliant on fixed-time traffic signals and manual data analysis, lack the flexibility required for real-time adjustments. We propose an ITS-AI framework leveraging machine learning algorithms to dynamically adjust signal timings based on real-time traffic data analysis. This approach optimizes traffic flow efficiency, denoted as η, and minimizes average travel time, represented by T. The objective is to enhance η by efficiently managing traffic density and flow, and to reduce T by optimizing signal timings, thereby facilitating smoother traffic conditions. Our dataset includes over 1 million data points from traffic sensors and cameras, encompassing traffic volume, speed, and environmental conditions. This rich dataset provides a comprehensive basis for training our AI models and testing their effectiveness in real-world scenarios. Application of the ITS-AI model has led to a 15% improvement in traffic flow efficiency (η) and a 20% reduction in average travel time (T), significantly outperforming traditional traffic management techniques. These results underscore the model’s ability to adapt to changing traffic conditions and to make real-time, data-driven decisions for signal timing optimization.The ITS-AI integration marks a substantial advancement in urban traffic management, offering a scalable and efficient solution for mitigating congestion. By applying a sophisticated mathematical approach to optimize η and reduce T, this framework sets a new standard for intelligent traffic systems in urban environments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    ITS-AI Integration: Enhanced Strategies for Mitigating Urban Traffic Congestion


    Beteiligte:


    Erscheinungsdatum :

    09.04.2024


    Format / Umfang :

    1004097 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Michigan Toolbox for Mitigating Traffic Congestion

    J. A. Crawford / T. B. Carlson / W. L. Eisele et al. | NTIS | 2011


    Bi-objective optimization models for mitigating traffic congestion in urban road networks

    Haritha Chellapilla / R. Sivanandan / Bhargava Rama Chilukuri et al. | DOAJ | 2023

    Freier Zugriff

    Next Road Rerouting: A Multiagent System for Mitigating Unexpected Urban Traffic Congestion

    Wang, Shen / Djahel, Soufiene / Zhang, Zonghua et al. | IEEE | 2016