An in-flight multimodal data collection method for assessing pilot cognitive states and performance in general aviation
MethodsX · 2025-12 · 15 · 103589
DOI: 10.1016/j.mex.2025.103589 ↗Kurz gefasst
Fachartikel in der Zeitschrift MethodsX, 2025-12. Verfasst von Rongbing Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Human factors are central to aviation safety, with pilot cognitive states such as workload, stress, and situation awareness playing important roles in flight performance and safety. Although flight simulators are widely used for training and scientific research, they often lack the ecological validity needed to replicate pilot cognitive states from real flights. To address these limitations, a new in-flight data collection methodology for general aviation using a Cessna 172 aircraft, which is one of the most widely used aircraft for pilot training, is presented. The dataset combines: • Human data from wearable physiological sensors (electroencephalography, electrocardiography, electrodermal activity, and body temperature) and eye-tracking glasses. • Flight data from ADS-B flight recorder. • Pilot's self-reported cognitive states and flight performance rate by instructor. The paper describes the sensor setup, flight task design, and data synchronization procedures. Potential analyses using statistical and machine learning methods are discussed to classify cognitive states and demonstrate the dataset's value. This methodology supports human factors research and has practical value for applications in pilot training, performance evaluation, and aviation safety management. The method was applied in a field study with 25 participants, from which 20 complete multimodal datasets were retained after data cleaning. After collecting additional data, the resulting dataset will support further research on pilot performance and behavior.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada.
- Waterloo Institute for Sustainable Aeronautics, University of Waterloo, Waterloo, ON, Canada.
- Department of Kinesiology and Health Sciences, University of Waterloo, Waterloo, ON, Canada.
- Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON, Canada.
- School of Optometry & Vision Science, University of Waterloo, Waterloo, ON, Canada.
- Department of Earth and Environmental Science, University of Waterloo, Waterloo, ON, Canada.
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Xu, R., Cao, S., Barnett-Cowan, M., Bulbul, G., Irving, E., Niechwiej-Szwedo, E., & Kearns, S. (2025). An in-flight multimodal data collection method for assessing pilot cognitive states and performance in general aviation. MethodsX, 15, 103589. https://doi.org/10.1016/j.mex.2025.103589
Vancouver
Xu R, Cao S, Barnett-Cowan M, Bulbul G, Irving E, Niechwiej-Szwedo E, et al. An in-flight multimodal data collection method for assessing pilot cognitive states and performance in general aviation. MethodsX. 2025;15:103589. doi:10.1016/j.mex.2025.103589
BibTeX
@article{Xu2025,
author = {Xu, Rongbing and Cao, Shi and Barnett-Cowan, Michael and Bulbul, Gulnaz and Irving, Elizabeth and Niechwiej-Szwedo, Ewa and Kearns, Suzanne},
title = {An in-flight multimodal data collection method for assessing pilot cognitive states and performance in general aviation},
journal = {MethodsX},
year = {2025},
volume = {15},
pages = {103589},
doi = {10.1016/j.mex.2025.103589}
}
EUVIMED