Detection of Pilot’s Mental Workload Using a Wireless EEG Headset in Airfield Traffic Pattern Tasks

Elevated mental workload (MWL) experienced by pilots can result in increased reaction times or incorrect actions, potentially compromising flight safety. This study aims to develop a functional system assist administrators identifying and detecting pilots’ real-time MWL evaluate its effectiveness using designed airfield traffic pattern tasks within realistic simulator. The perceived various situations was assessed labeled NASA Task Load Index (NASA-TLX) scores. Physiological features were then extracted fast Fourier transformation with 2-s sliding time windows. Feature selection conducted comparing the results of Kruskal-Wallis (K-W) test Sequential Forward Floating Selection (SFFS). proved that optimal input all PSD features. Moreover, analyzed effects electroencephalography (EEG) from distinct brain regions changes across different levels further assess proposed system’s performance. A 10-fold cross-validation performed on six classifiers, accuracy 87.57% attained multi-class K-Nearest Neighbor (KNN) classifier for classifying levels. findings indicate wireless headset-based is reliable feasible. Consequently, numerous EEG device-based systems be developed application diverse real-driving scenarios. Additionally, current contributes future research actual conditions.