A Multimodal Cluster-Aware Learning Framework for Pilot Cognitive-State Recognition Using EEG and Peripheral Physiological Signals
Engineering, Technology & Applied Science Research · 11.08.2026 · 16 (4) · 37306-37316
DOI: 10.48084/etasr.18805 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 11.08.2026. Verfasst von Quynh Anh Nguyen und 1 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Loss of state awareness remains a major contributor to aviation incidents, motivating the need for reliable and interpretable monitoring of pilot cognitive states. This study presents a multimodal cluster-aware learning framework for pilot cognitive-state recognition using Electroencephalography (EEG), Electrocardiography (ECG), Galvanic Skin Response (GSR), and respiration signals. The framework combines modality-aware preprocessing, hybrid dimensionality reduction through principal component analysis and an autoencoder, latent-structure discovery via k-means clustering, and cluster-specific classification using Light Gradient Boosting Machine (LGBM). Experiments were conducted on the public Kaggle benchmark Reducing Commercial Aviation Fatalities, which contains synchronized psychophysiological recordings from 18 pilots under four induced mental states. Under a stratified 5-fold benchmark protocol, the proposed method achieved an overall accuracy of 0.956, outperforming XGBoost, multilayer perceptron, and several representative baselines. The results indicate that multimodal fusion and cluster-aware classification improve the representation of heterogeneous psychophysiological patterns while maintaining computational tractability. Although additional subject-independent validation remains necessary to establish stronger generalization claims, the proposed framework provides a structured and scalable foundation for cognitive-state monitoring in aviation environments.
Zitieren
APA
Nguyen, Q. A., & Dao, N. A. (2026). A Multimodal Cluster-Aware Learning Framework for Pilot Cognitive-State Recognition Using EEG and Peripheral Physiological Signals. Engineering, Technology & Applied Science Research, 16(4), 37306-37316. https://doi.org/10.48084/etasr.18805
Vancouver
Nguyen QA, Dao NA. A Multimodal Cluster-Aware Learning Framework for Pilot Cognitive-State Recognition Using EEG and Peripheral Physiological Signals. Engineering, Technology & Applied Science Research. 2026;16(4):37306-37316. doi:10.48084/etasr.18805
BibTeX
@article{Nguyen2026,
author = {Nguyen, Quynh Anh and Dao, Nam Anh},
title = {A Multimodal Cluster-Aware Learning Framework for Pilot Cognitive-State Recognition Using EEG and Peripheral Physiological Signals},
journal = {Engineering, Technology & Applied Science Research},
year = {2026},
volume = {16},
number = {4},
pages = {37306--37316},
doi = {10.48084/etasr.18805}
}
EUVIMED