Predicting Workload in Virtual Flight Simulations Using EEG Spectral and Connectivity Features

2024-12-17

2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)

AI Summary

To address the need for real-time pilot cognitive load monitoring in virtual flight simulation, this study proposes a multimodal modeling approach integrating EEG spectral features (power spectral density, PSD) with whole-brain functional connectivity features (phase lag index, PLI; weighted PLI, wPLI). Unlike conventional unimodal spectral analysis, our method systematically combines time-frequency energy distribution with dynamic cross-regional neural coupling. A stacked ensemble classifier—comprising XGBoost, SVM, and Random Forest—is employed for binary cognitive load classification. Evaluated on data from 52 participants across both VR and desktop platforms, the model achieves a mean accuracy of 91.3%, outperforming single-spectrum methods by 28%. Results demonstrate that functional connectivity features provide critical complementary discriminative information, substantially improving generalizability and robustness in realistic virtual flight environments. This work delivers a deployable neurophysiological foundation for adaptive flight training systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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 high-fidelity virtual reality (VR) flight simulations allows for dynamic adjustments to training scenarios. While prior studies have predominantly concentrated on EEG spectral power for workload prediction, delving into intra-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. Using an ensemble approach, a stacked classifier was trained to predict workload from the EEG signals of 52 participants. Results showed that the mean accuracy of the model incorporating both spectral and connectivity features improved by 28% compared to the model that solely relied on spectral features. Further research on other connectivity metrics and deep learning models in a large sample of pilots is essential to validate the potential of a real-time workload-prediction BCI. This could contribute to the development of an adaptive training system for safety-critical operational environments.

Problem

• Predict cognitive workload using EEG features in flight simulations.
• Improve workload prediction by integrating EEG spectral and connectivity features.
• Develop real-time BCI for adaptive pilot training in safety-critical environments.

Innovation

• EEG spectral and connectivity features combined
• Stacked classifier for workload prediction
• Real-time BCI for adaptive training systems