Improving pilot mental workload classification through feature exploitation and combination: a feasibility study

Abstract

Predicting high pilot mental workload is important to the United States Air Force because lives and aircraft have been lost due to errors made during periods of flight associated with mental overload and task saturation. Current research efforts use psychophysiological measures such as electroencephalography (EEG), cardiac, ocular, and respiration measures in an attempt to identify and predict mental workload levels. Existing classification methods successfully classify pilot mental workload using flight data for a single pilot on a given day, but are unsuccessful across different pilots and/or days. We demonstrate a small subset of combined and calibrated psychophysiological features collected from a single pilot on a given day that accurately classifies mental workload for a separate pilot on a different day. We achieve classification accuracy (CA) improvements over previous classifiers exceeding 80% while using significantly fewer features and dramatically reducing the CA variance. Without the need for EEG data, our feature combination and calibration scheme also radically reduces the raw data collection requirements, making data collection immensely easier to manage and spectacularly reducing computational processing requirements.