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

DOI

10.2991/978-94-6463-082-4_12How to use a DOI?

Keywords

Deep Learning; Vehicle Diagnostics; Physiology; Remote Sensing; Hybrid Features; Real time; Driver Drowsiness Detection

Abstract

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.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Em Poh Ping
AU  - Teoh Tai Shie
PY  - 2022
DA  - 2022/12/23
TI  - Driver Drowsiness Detection System Using Hybrid Features Among Malaysian Drivers: A Concept
BT  - Proceedings of the Multimedia University Engineering Conference (MECON 2022)
PB  - Atlantis Press
SP  - 108
EP  - 120
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-082-4_12
DO  - 10.2991/978-94-6463-082-4_12
ID  - Ping2022
ER  -