Intelligent transportation systems greatly benefit from lane-changing (LC) driving behaviour when it comes to safety. Because drivers' actions are so random, it's hard to made the LC process. It is a high risk of serious accidents caused by irrational lane changes and the resulting traffic congestion. Right now, lane shifting models aren't very accurate. Therefore, very accurate lane change prediction is necessary to enhance road safety. A good lane change forecast model based on the Deep Belief Network (DBN) model has been created to learn about people's risky lane changing habits. Bayesian networks using Gaussian mixture models and back propagation neural networks are two examples of state-of-the-art methods that are contrasted with the suggested model. The Bayesian network with a Gaussian mixture model and back propagation neural network predict dangerous driving behaviour less accurately than the suggested approach. An accuracy percentage of 97.2% was achieved with the Deep Belief Network model. The outcomes implies, the suggested method is highly efficient in predicting when a driver will switch lanes. An intelligent transportation system may alert drivers of unsafe lane alterations by the suggested method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Learning-Based Efficient Framework for Predicting Lane Change


    Contributors:


    Publication date :

    2024-12-11


    Size :

    712737 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Modeling Framework for Predicting Lane Change Intensity at Freeway Weaving Segments

    Ahmed, Ishtiak / Karr, Alan / Rouphail, Nagui M. et al. | Transportation Research Record | 2023


    Vehicle Lane Change Prediction on Highways Using Efficient Environment Representation and Deep Learning

    IZQUIERDO GONZALO Rubén / QUINTANAR PASCUAL Álvaro / LORENZO DÍAZ Javier et al. | BASE | 2021

    Free access

    Time-to-lane-change prediction with deep learning

    Dang, Hien Q. / Furnkranz, Johannes / Biedermann, Alexander et al. | IEEE | 2017



    Lane-GNN: Integrating GNN for Predicting Drivers' Lane Change Intention

    Wu, Hongde / Liu, Mingming | ArXiv | 2022

    Free access