A regression model combined convolutional neural network and recurrent neural network for electroencephalogram-based cross-subject fatigue detection

• Published in: Review of scientific instruments Vol. 94; no. 9
• Main Authors: Yuan, Duanyang, Yue, Jingwei, Xu, Huiyan, Wang, Yuanbo, Zan, Peng, Li, Chunyong
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 01.09.2023
• Subjects: Artificial neural networks; Classification; Correlation coefficients; Deep learning; Design of experiments; Electroencephalography; Feature extraction; Machine learning; Neural networks; Recurrent neural networks; Regression models; Root-mean-square errors; Sampling methods; Scientific apparatus & instruments; Traffic safety

Fatigue, one of the most important factors affecting road safety, has attracted many researchers’ attention. Most existing fatigue detection methods are based on feature engineering and classification models. The feature engineering is greatly influenced by researchers’ domain knowledge, which will...