Vehicle obstruction is a special scenario in vehicle-to-vehicle (V2V) communications. In this case, channel characteristics including path loss and spatial distributions are obviously different from other typical vehicular communication scenarios. However, the vehicle obstruction scenario is difficult to be identified by global navigation satellite systems (GNSS) or radars, so it is difficult for V2V communication systems to respond to sudden changes in channel characteristics due to vehicle obstructions. Therefore, by correctly identifying the vehicle obstruction scenarios, V2V communication systems can select appropriate propagation channel models to maintain an effective and reliable operating state. For this reason, this paper presents a machine-learning-based vehicle obstruction scenario identification approach for V2V communications. Channel characteristics extracted from measurements form the datasets used to training, then the back-propagation neural network (BPNN) is trained and a scenario identification model is obtained. Subsequently, identification accuracy is verified by using validation data. The results show that the identification accuracy for vehicle obstruction scenarios is more than 97%, which indicates that the approach proposed in this paper shows good performance in vehicle obstruction scenario identification in V2V communications.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Identification of Vehicle Obstruction Scenario Based on Machine Learning in Vehicle-to-vehicle Communications


    Contributors:
    Yang, Mi (author) / Ai, Bo (author) / He, Ruisi (author) / Huang, Chen (author) / Li, Jianzhi (author) / Ma, Zhangfeng (author) / Chen, Liang (author) / Li, Xue (author) / Zhong, Zhangdui (author)


    Publication date :

    2020-05-01


    Size :

    208078 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Vehicle scenario mining for machine learning models

    KABZAN JURAJ / GOMES JULIA | European Patent Office | 2023

    Free access

    Vehicle obstruction detection

    GUPTA VISHISHT VIJAY / PRADOS MICHAEL | European Patent Office | 2017

    Free access



    Line-of-Sight Obstruction Analysis for Vehicle-to-Vehicle Network Simulations in a Two-Lane Highway Scenario

    Abbas, Taimoor / Tufvesson, Fredrik / Kürner, Thomas | Tema Archive | 2013