Driver fatigue state detection based on EEG and EOG feature fusion and deep learning

Ying Yang; Hong Xie; Xian Xie

doi:10.1117/12.2618730

29 November 2021 Driver fatigue state detection based on EEG and EOG feature fusion and deep learning

Ying Yang, Hong Xie, Xian Xie

Proceedings Volume 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021); 120800M (2021) https://doi.org/10.1117/12.2618730
Event: 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 2021, Nanchang, China

Abstract

Fatigue driving is an important factor leading to traffic accidents, often causing serious consequences. Therefore, real-time detection of driver fatigue is the key to avoid fatigue driving. Aiming at the single detection standard that can easily reduce the accuracy of driver fatigue detection, a neural network method based on the multi-modal fusion of forehead EEG and ocular signals is proposed to fully mine the complementary information of the two signal characteristics, and using SEEDVIG, the public data set of Shanghai Jiao tong University for training. The experimental results show that compared with a single modal. Multi-modal fusion has a better recognition effect for fatigue detection, and its accuracy rate reaches 96.43%, which is helpful to promote the application of the fatigue detection system based on EEG signals in the driving process of the driver.

Citation Download Citation

Ying Yang, Hong Xie, and Xian Xie "Driver fatigue state detection based on EEG and EOG feature fusion and deep learning", Proc. SPIE 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 120800M (29 November 2021); https://doi.org/10.1117/12.2618730

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available