Assessing human situation awareness reliability considering fatigue and mood using EEG data: A Bayesian neural network-Bayesian network approach

Situation awareness (SA) assessment is the process of acquiring and maintaining SA, which serves as a crucial indicator of operator task performance and behavioral safety in human-machine interaction. SA reliability is the evaluation of how well SA is established, and it is also the goal of SA assessment. Nonetheless, current SA assessment models rarely consider the influence of human physiological states, such as fatigue and mood, and rely heavily on subjective data. To address these deficiencies, this paper proposes a SA assessment model based on a Bayesian Neural Network (BNN) and Bayesian Network (BN), with a focus on examining the impact of fatigue and mood on the SA reliability. Firstly, fatigue and mood state classification models are developed using EEG data based on a BNN, and the uncertainty is assessed. Secondly, a BN model for SA reliability evaluation is proposed, where the uncertainty of BNN outputs is used as the prior probability, and conditional probability tables are established based on experimental statistics. Finally, a SA experiment is conducted using a civil aviation scenario based on the SAGAT platform to validate the proposed model. This model overcomes the limitations of previous approaches by leveraging objective physiological data and experimental statistics to infer the influence of physiological states on the SA reliability.