Pilot Fear Detection from EEG Signals Classified by Decision Tree During Landing Conditions

This research addresses the critical issue of fear detection in pilots within the aviation domain, recognizing its profound impact on performance and flight safety. By leveraging Electroencephalogram (EEG) data and employing a Decision Tree algorithm, this study aims to discern varying levels of fear experienced by pilots, particularly during the crucial landing phase. EEG signals were collected during simulated flight operations, categorized into five fear levels, ranging from none to extreme. Evaluation of the model's performance, utilizing a confusion matrix, revealed an impressive average accuracy of 92.95%. The potential application of this system as a tool for identifying fear in aspiring pilots holds promise for enhancing overall flight safety standards.