Fine-Grained Mental Workload Estimation Based on Eeg Signal Analysis

Mental workload, as a crucial indicator reflecting the intensity of human brain activity, can be utilized to assess the suitability of continuing with a given task. Prolonged highintensity mental activities are detrimental to brain health, leading to a decline in cognitive abilities and reaction speeds, which must be avoided in high-risk task environments. In this thesis, we devised an algorithm that, through the analysis of electroencephalogram (EEG) data collected from pilots engaged in tasks of varying difficulty, derives a fine-grained mental workload profile (ranging from 1 to 100) that varies over time. This algorithm provides real-time feedback on the intensity of mental activity and serves as a basis for safety evaluations.