InstanceEasyTL: An Improved Transfer-Learning Method for EEG-Based Cross-Subject Fatigue Detection

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 24; p. 7251
• Main Authors: Zeng, Hong, Zhang, Jiaming, Zakaria, Wael, Babiloni, Fabio, Gianluca, Borghini, Li, Xiufeng, Kong, Wanzeng
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 17.12.2020; MDPI
• Subjects: Automobile Driving; Classification; cross-subject; Discriminant analysis; Electroencephalogram (EEG); Electroencephalography; Experiments; Fatigue - diagnosis; fatigue driving; Humans; InstanceEasyTL; Machine Learning; Neural networks; Neural Networks, Computer; Questionnaires; Support Vector Machine; Support vector machines; Traffic; transfer learning; transfer learning; Electroencephalogram (EEG); cross-subject; fatigue driving; InstanceEasyTL
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20247251

Electroencephalogram (EEG) is an effective indicator for the detection of driver fatigue. Due to the significant differences in EEG signals across subjects, and difficulty in collecting sufficient EEG samples for analysis during driving, detecting fatigue across subjects through using EEG signals remains a challenge. EasyTL is a kind of transfer-learning model, which has demonstrated better performance in the field of image recognition, but not yet been applied in cross-subject EEG-based applications. In this paper, we propose an improved EasyTL-based classifier, the InstanceEasyTL, to perform EEG-based analysis for cross-subject fatigue mental-state detection. Experimental results show that InstanceEasyTL not only requires less EEG data, but also obtains better performance in accuracy and robustness than EasyTL, as well as existing machine-learning models such as Support Vector Machine (SVM), Transfer Component Analysis (TCA), Geodesic Flow Kernel (GFK), and Domain-adversarial Neural Networks (DANN), etc.