A novel method of mental fatigue detection based on CNN and LSTM. (4th June 2021)

• Record Type: Journal Article
• Authors: Zhang, Shaohan; Zhang, Zhenchang; Chen, Zelong; Lin, Shaowei; Xie, Ziyan
• Is Part Of: International journal of computational science and engineering. Volume 24:Number 3(2021)
• Page Start: 290
• Page End: 300
• Publication Date: 2021-06-04
• Subjects: electroencephalography -- EEG -- mental fatigue detection -- wavelet threshold denoising -- fatigue scale -- CNN -- CNN + LSTM; Computer science -- Mathematics -- Periodicals; Computer simulation -- Mathematical aspects -- Periodicals; Computational intelligence -- Periodicals; 004.015105
• Languages: English
• ISSNs: 1742-7185

Abstract

Mental fatigue is a state that may occur due to excessive work or long-term stress. Electroencephalography (EEG) is considered a reliable standard for mental fatigue detection. The existing EEG fatigue detection methods mainly use traditional machine learning models to classify mental fatigue after manual feature extraction. However, manual feature extraction is difficult and complicated. The quality of feature extraction largely determines the quality of the model. In this article, we collected EEG signals from 30 medical staff. The wavelet threshold denoising method was then applied to the measured EEG signal data to denoise the original EEG data, and a method based on a convolution and long short-term memory (CNN + LSTM) neural network to determine the fatigue state of medical staff. The extensive experiment on the established dataset clearly proves the advancement of our proposed algorithm compared to other neural network-based methods. Compared with the existing DNN, CNN and LSTM, the proposed model can quickly learn the information before and after the time series, so as to obtain higher classification accuracy.