The exponential increase in the number of automobiles on the road has caused pollution, gridlock, and logistical transit delays in densely populated places. A new invention, the Internet of Things (IoT) is guiding the cosmos towards intelligent management systems and automated procedures. The advancement of automation and smart societies relies on this management of congestion and traffic control that are both effective and dependable and can save a lot of valuable resources. Autonomous cars and smart gadgets use an Internet of Things (IoT)-based ITM system of sensors to detect, collect, and communicate data. The transportation system may also benefit from machine learning (ML). Many problems plague current transport management methods, leading to gridlock, delays, and a high number of casualties. This study details the process of developing and launching an ATM that makes use of machine learning and the Internet of Things. Transportation, physical structures, and occurrences are the three pillars upon which the suggested system rests. The design takes into account every potential difficulty with the transportation system by using many scenarios. Using the machine learning-based DBSCAN clustering technology, the suggested ATM systems further guarantee that no inadvertent abnormalities are overlooked. The proposed ATM model can adapt the timing of the traffic lights based on current conditions as well as predicted movements at nearby crossings. Reducing traffic congestion eases vehicles over green lights and shortens travel times by improving the transition between turns. The experimental findings show that the proposed ATM system significantly outperformed the conventional traffic-management method, making it the ideal candidate for use in smart-city-based transportation planning. The proposed ATM system aims to reduce road accidents, improve the overall route experience, and minimise vehicle waiting durations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Implementing ML and IoT-Based Predictive Traffic-Management Systems for Smart Cities


    Contributors:


    Publication date :

    2024-11-15


    Size :

    1545757 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    AI-Driven Traffic Congestion Management: A Predictive Analytics Approach for Smart Cities

    Rathore, Saurabh Pratap Singh / Farhaoui, Yousef / Aniebonam, Ebuka Emmanuel et al. | IEEE | 2025


    IoT Based Traffic Management in Smart Cities

    Farheen, Asma / Ashwini, S. / Priyanka, K. G. et al. | Springer Verlag | 2018


    TrafficIntel: Smart traffic management for smart cities

    Saikar, Anurag / Parulekar, Mihir / Badve, Aditya et al. | IEEE | 2017


    Advanced Traffic Management System for Smart Cities

    Nijim, Mais / Kanumuri, Viswas / Alaqqad, Waseem et al. | Springer Verlag | 2023


    A Sustainable Traffic Management System for Smart Cities

    Bhatt, Arpit Kumar / Goyal, Deepanshu / Biswas, Susham | Springer Verlag | 2023

    Free access