Driver Fatigue Detection Based on Multiple Physiological Signals and an Improved Deep Belief Network

Authors

  • Lin Wang Shenyang Institute of Engineering
  • Yuxuan Liu Shenyang Institute of Engineering
  • Xiaowei Yin Shenyang Institute of Engineering
  • Jiaqi Li Shenyang Institute of Engineering
  • Yulin Gu Shenyang Institute of Engineering

DOI:

https://doi.org/10.5755/j01.itc.54.1.39833

Keywords:

Driver fatigue, EMG signal, EEG signal, Feature parameters, Deep Belief network

Abstract

In order to accurately discriminate the driver fatigue, multiple physiological signals of 10 drivers were collected by a wireless body area network in actual driving, including neck electromyography (EMG) and electroencephalography (EEG). Then, the noises of signals were removed by several denoising methods, and 22 features were extracted, including energy entropy, multiscale entropy, and other relevant features. Subsequently, a deep belief network (DBN) was used to further extract multi-domain features. And then, a grey wolf optimization algorithm was used to optimize the performance of the DBN. The results showed that the accuracy of the model built in the present work was up to 96% in discriminating the fatigue states.

Downloads

Published

2025-04-01

Issue

Section

Articles