Recognition of fatigue status of pilots based on deep contractive auto-encoding network.
10.7507/1001-5515.201701018
- Author:
Shuang HAN
1
;
Qi WU
2
;
Libing SUN
3
;
Xuyi QIU
4
;
He REN
5
;
Zhao LU
6
Author Information
1. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, P.R.China.han1201@sjtu.edu.cn.
2. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, P.R.China.
3. Shanghai Securtech Information Technology Co., ltd. Shanghai 200240, P.R.China.
4. Chinese Aeronautical Radio Electronics Research Institute, Shanghai 200240, P.R.China.
5. Shanghai Engineering Research Center of Civil Aircraft Health Monitoring, Shanghai 200240, P.R.China.
6. Department of Electrical Engineering, Tuskegee University, Tuskegee, AL 36088, USA.
- Publication Type:Journal Article
- Keywords:
deep contractive auto-encoding network;
electroencephalogram signals;
pilots’ fatigue;
wavelet packet transform
- From:
Journal of Biomedical Engineering
2018;35(3):443-451
- CountryChina
- Language:Chinese
-
Abstract:
We proposed a new deep learning model by analyzing electroencephalogram signals to reduce the complexity of feature extraction and improve the accuracy of recognition of fatigue status of pilots. For one thing, we applied wavelet packet transform to decompose electroencephalogram signals of pilots to extract the δ wave (0.4-3 Hz), θ wave (4-7 Hz), α wave (8-13 Hz) and β wave (14-30 Hz), and the combination of them was used as de-nosing electroencephalogram signals. For another, we proposed a deep contractive auto-encoding network-Softmax model for identifying pilots' fatigue status. Its recognition results were also compared with other models. The experimental results showed that the proposed deep learning model had a nice recognition, and the accuracy of recognition was up to 91.67%. Therefore, recognition of fatigue status of pilots based on deep contractive auto-encoding network is of great significance.
