A Master of Science thesis in Biomedical Engineering by Nadia Khalil Mohammad Abu Farha entitled, “Vigilance Assessment Using EEG and Eye Tracking Data Fusion”, submitted in April 2021. Thesis advisor is Dr. Hasan Al-Nashash and thesis co-advisors are Dr. Fares Yahya and Dr. Usman Tariq. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).
Abstract
Vigilance describes the ability to maintain alertness while performing a task for a prolonged time. Maintaining vigilance is one of the requirements in many workplaces, especially those that rely on monitoring, such as: surveillance tasks, security monitoring, and air traffic control. These tasks necessitate a specific level of arousal, to provide an acceptable level of cognitive efficiency. Vigilance decrement could result in fatal consequences like accidents, loss of life, and system failure. In this thesis, we investigated the possibility of assessing the vigilance levels using a fusion of Electroencephalography (EEG) and eye tracking data. Vigilance levels are induced by performing a modified version of Stroop Color-Word Task (SCWT) for 30 minutes. Feature-level fusion based on the canonical correlation analysis (CCA) has been employed to enhance the classification accuracy for vigilance level assessment. In the feature level fusion, EEG and eye tracking features are concatenated into a single vector-feature-space and then fed as an input to the Support Vector Machine classifier. The results of the fusion showed that both modalities’ accuracies have been enhanced. The highest accuracy for the fusion was using the EEG Delta band of 96.8± 0.6%, which is higher than using the EEG Delta band without the fusion (88.18±8.5%) or the eye tracking date alone (76.8 ± 8.4 %).