Enhanced Cognitive Load Detection in Air Traffic Control Operators Using EEG and a Hybrid Deep Learning Approach

Abstract

The automatic and effective detection of cognitive load for air traffic control (ATC) operators through electroencephalography (EEG) signals provides a covert and objective method for enhancing ATC safety. Nevertheless, the extant paradigm is limited to simple cognitive tasks and lacks real-world scenarios. In this study, a cognitive load-elicited experiment was therefore designed to record the EEG data of eight ATC operators under four distinct simulation scenarios, ascertaining whether they experienced varying degrees of workload. Subsequently, the collected EEG signal was preprocessed. We then used one hybrid deep learning model based on the convolutional layers and a self-attention mechanism to extract the pertinent EEG features. In conjunction with multi-layer perceptron, we decoded cognitive load state into low, high, overload, and special. The experimental results demonstrated that EEG could serve as a reliable measure for predicting ATC load, with an average accuracy of 88.76% and a peak accuracy of 99% at the single-subject level. Additionally, it highlighted the critical role of the frontal regions in decoding cognitive load. This study serves to enhance the efficacy of personalized EEG decoding for ATC operators, furnishing evidence for the feasibility of developing an intelligent load-detecting system.