

Transformer-Based Estimation of Pilot Cognitive Workload Using Self-Supervised Multimodal Biometric Learning
Abstract
Accurately estimating a pilot’s cognitive workload is essential for enhancing aviation safety and fostering the development of intelligent cockpit systems. Conventional machine learning models, though effective in narrowly defined domains, often struggle to generalize across diverse flight conditions. This paper presents a comparative study of two workload classification approaches. They are: transfer learning using the convolutional BM3TX architecture and a Transformer-based model inspired by the Joint Embedding Predictive Architecture (JEPA). Using biometric data collected from 89 pilots performing simulated turbulence maneuvers, our results demonstrate that the JEPA-inspired model significantly outperforms the traditional approach in both accuracy (70.6% vs. 63.8%) and interpretability. Attention-based visualizations provide additional insight into the decision-making process, offering a foundation for scalable, explainable pilot monitoring systems.
References
Ćosić, Krešimir, Siniša Popović, and Brenda K. Wiederhold. "Enhancing aviation safety through AI-driven mental health management for pilots and air traffic controllers." Cyberpsychology, Behavior, and Social Networking 27.8 (2024): 588-598.
Ćosić, K., Popović, S., & Wiederhold, B. K. (2024). Enhancing aviation safety through AI-driven mental health management for pilots and air traffic controllers. Cyberpsychology, Behavior, and Social Networking, 27(8), 588-598.
Perumal, Uma. "Application Of Machine Learning For Pilots Training."
Ćosić K, Popović S, Wiederhold BK. Enhancing aviation safety through AI-driven mental health management for pilots and air traffic controllers. Cyberpsychology, Behavior, and Social Networking. 2024 Aug 1;27(8):588-98.
Mohanavelu, K., et al. "Machine learning-based approach for identifying mental workload of pilots." Biomedical Signal Processing and Control 75 (2022): 103623.
Mohanavelu, K., S. Poonguzhali, A. Janani, and S. Vinutha. "Machine learning-based approach for identifying mental workload of pilots." Biomedical Signal Processing and Control 75 (2022): 103623.
Mohanavelu, K., Poonguzhali, S., Janani, A., & Vinutha, S. (2022). Machine learning-based approach for identifying mental workload of pilots. Biomedical Signal Processing and Control, 75, 103623.
Lam, Steven Tze Fung, and Alan Hoi Shou Chan. "Application of Artificial Intelligence, Machine Learning and Deep Learning in Piloted Aircraft Operations: Systematic." (2024).
Lam, S. T. F., & Chan, A. H. S. (2024). Application of Artificial Intelligence, Machine Learning and Deep Learning in Piloted Aircraft Operations: Systematic.
Refbacks
- There are currently no refbacks.