Abstract:Effective cognitive workload management has a major impact on the safety and performance of pilots. Integrating brain-computer interfaces (BCIs) presents an opportunity for real-time workload assessment. Leveraging cognitive workload data from immersive, high-fidelity virtual reality (VR) flight simulations enhances ecological validity and allows for dynamic adjustments to training scenarios based on individual cognitive states. While prior studies have predominantly concentrated on EEG spectral power for workload prediction, delving into inter-brain connectivity may yield deeper insights. This study assessed the predictive value of EEG spectral and connectivity features in distinguishing high vs. low workload periods during simulated flight in VR and Desktop conditions. EEG data were collected from 52 non-pilot participants conducting flight tasks in an aircraft simulation, after which they reported cognitive workload using the NASA Task Load Index. Using an ensemble approach, a stacked classifier was trained to predict workload using two feature sets extracted from the EEG data: 1) spectral features (Baseline model), and 2) a combination of spectral and connectivity features (Connectivity model), both within the alpha, beta, and theta band ranges. Results showed that the performance of the Connectivity model surpassed the Baseline model. Additionally, Recursive Feature Elimination (RFE) provided insights into the most influential workload-predicting features, highlighting the potential dominance of parietal-directed connectivity in managing cognitive workload during simulated flight. Further research on other connectivity metrics and alternative models (such as deep learning) in a large sample of pilots is essential to validate the possibility of a real-time BCI for the prediction of workload under safety-critical operational conditions.
Abstract:In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. This being an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we include results from an example data analytics application of our proposed approach, showcase novel analysis options, and discuss possible implications of the results from the perspective of teamwork research.