Drowsiness is one of the most critical factors contributing to a high number of crashes in Malaysia. Several types of driver drowsiness detection (DDD) systems have been developed to tackle this problem. They are based on vehicle diagnostics, physiology, or facial recognition. However, these systems have several limitations in terms of reliability and intrusiveness. Therefore, a hybrid approach based on vehicle diagnostics, physiology, and remote sensing information is proposed to tackle this problem. The training and test data are collected from the test subjects by driving the instrumented vehicle on North-South Expressway at 4 different periods: morning, afternoon, evening, and night. The training data is then used to train the deep learning model in classifying the driver’s drowsiness. A recurrent neural network is used in the system because it has a temporal characteristic that can be utilised to predict the driver’s drowsiness. It can also incrementally learn the features through backpropagation. Once the DDD system is developed, the test data is fed into the deep learning model to determine the model’s accuracy in drowsiness detection. Lastly, the test subjects must drive the car with the DDD system at 4 different periods. The hybrid features and deep learning are expected to enhance driver drowsiness detection accuracy compared to existing techniques. A survey is conducted to investigate the possibility of promoting the proposed system to other drivers in Malaysia.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Driver Drowsiness Detection System Using Hybrid Features Among Malaysian Drivers: A Concept


    Weitere Titelangaben:

    Advances in Engineering res


    Beteiligte:
    bin Alias, Mohamad Yusoff (Herausgeber:in) / Ping, Em Poh (Autor:in) / Shie, Teoh Tai (Autor:in)

    Kongress:

    Proceedings of the Multimedia University Engineering ; 2022 ; Cyberjaya and Melaka, Malaysia July 25, 2022 - July 27, 2022



    Erscheinungsdatum :

    23.12.2022


    Format / Umfang :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Driver Drowsiness Detection System

    Mahapatra, Pratik / Raj, Shivam / Biswas, Amrita | Springer Verlag | 2022


    Driver drowsiness detection system

    Alshaqaqi, Belal / Baquhaizel, Abdullah Salem / Amine Ouis, Mohamed El et al. | IEEE | 2013


    Driver Drowsiness Detection System

    Khan, Rimsha Mehnaaz / Kumar, B P Pradeep / Kabir, Sidra et al. | IEEE | 2025


    Driver drowsiness detection

    YANG HSIN-HSIANG / PRAKAH-ASANTE KWAKU O | Europäisches Patentamt | 2015

    Freier Zugriff

    Driver Drowsiness Detection

    Satish, K. / Lalitesh, A. / Bhargavi, K. et al. | IEEE | 2020