The rapid increase in road traffic has significantly contributed to urban air pollution, excessive fuel consumption, and toxic emissions, necessitating sustainable mobility solutions. This paper introduces the Sustainable Route Recommendation System (SRRS), a smart system that helps find the best driving routes to reduce carbon dioxide (CO2) and nitrogen oxide (NOx) emissions, save fuel, and shorten travel time. SRRS combines two important algorithms: the first is a YOLO-based model that quickly identifies and sorts vehicles into heavy and light types, and the second is a SUMO-based traffic simulation that suggests the best routes based on the type of vehicle. By intelligently distributing traffic, the system reduces congestion and enhances sustainability. Simulations at Apex Circle, Jaipur, show that SRRS reduces CO2 emissions by 30.05%, NOx emissions by 31.97%, and fuel consumption by 30.2% compared to conventional methods. These findings establish SRRS as a promising solution for sustainable urban mobility, reducing environmental impact while improving traffic efficiency.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    SRRS: A Sustainable Route Recommendation System using Advanced YOLO and SUMO


    Contributors:


    Publication date :

    2025-05-12


    Size :

    386139 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Shipboard Readiness Report System (SRRS) Software Prototype

    M. Vineberg / S. Connors / T. Sterrett et al. | NTIS | 1992


    SUMO in SPACE: Combining SUMO and dSPACE for Advanced Traffic Simulation

    Christopher Stang / Dennis Roeser | DOAJ | 2025

    Free access

    Google Maps Route Color Mapping with SUMO Simulator

    Mena, Ricardo / Zumarraga, Felipe / Urquiza, Luis et al. | IEEE | 2019


    Reinforcement Learning for Vehicle Route Optimization in SUMO

    Koh, Song Sang / Zhou, Bo / Yang, Po et al. | IEEE | 2018