PhD thesis defense to be held on December 19, 2024, at 13:00 (NTUA Central Library)
Thesis title: Development of Driving Fatigue Detection System using Machine Learning Techniques
Abstract: Mental fatigue during driving refers to the cognitive strain experienced by drivers over extended periods, which can impair attention, reaction times, and overall driving performance. Driving fatigue presents significant risks to road safety and requires accurate assessment methods to mitigate potential hazards. This dissertation focuses on the development and evaluation of innovative methods for detecting mental fatigue during driving, emphasizing individualized approaches and advanced techniques for brain network analysis. Utilizing EEG signals and Phase Lag Index (PLI), combined with machine learning algorithms, the research highlights the importance of understanding individual connectivity patterns in predicting fatigue dynamics. The incorporation of source localization techniques provided high-resolution mapping of specific brain regions involved in fatigue processes, revealing the critical role of the alpha frequency band in identifying mental fatigue. Additionally, sensor-level analyses offered practical solutions for real-time applications due to their simplicity and efficiency. These findings underscore the potential for advancing fatigue detection methodologies through the integration of neuroscientific insights and application-driven strategies.
Supervisor: Professor Emeritus Dimitris Koutsouris
PhD Student: Olympia Giannakopoulou