Neuro - ergonomic Research for Online Assessment of Cognitive Workload

This paper investigates mental workloadassessment using statistical features derived fromelectroencephalography (EEG) signals. Mean, root meansquared, and correlation-based features are extracted from dataincluding EEG signal recordings of five participants performinga reading task with three difficulty levels of low, medium, andhigh and a baseline condition. Results reveal that for the giventask, features derived from the EEG signals consistently exhibita very high degree of discrimination between the induced loadlevels, confirming EEG as an important method for the real time,objective determination of cognitive load level. Also, the frontalEEG channels appear to be sensitive to the working memoryload than the other channels. Analysis of the effect of the windowlength used during feature extraction from the EEG signalssuggest that features extracted from EEG segments as short as1 second exhibit an acceptable amount of standard deviation,suggesting that EEG-based measurement of fairly rapid changesin cognitive load may be feasible.