EEG-based fatigue recognition using deep learning techniques

• Main Author: Zheng, Tianhu
• Other Authors: Wang Lipo
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering::Computer applications::Life and medical sciences; Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics
• Online Access: https://hdl.handle.net/10356/155413
• Institution: Nanyang Technological University

Mental fatigue has been proven to have a huge impact on the safety of human society. As mental fatigue will dramatically reduce the concentration and reaction time of workers or drivers, mistakes and devastating consequences will occur. Therefore early detection of mental fatigue is an imperative solution to decrease the disaster. With the development in bio-sensory technology, EEG which can detect the electrical signal of neural activity from the scalp has provided valuable prospects to understand human brain activity. Through EEG signals we can discover the hidden hints between brainwave and mental fatigue. Recent research about deep learning has made many breakthroughs in areas like Image Process and Natural Language Processing and achieved impressive results. This dissertation mainly studies attention-based deep learning techniques for recognizing mental fatigue and achieved an average accuracy of more than 73%. And proposed a single channel-based visualization technique to interpret the classification principle of the deep learning algorithm.