SavedAdd your journal

Journals / Electronic Letters on Science and Engineering / 2026 / Volume: 22 Issue: 1

Electrode and Frequency Band Importance for EEG-Based Mission-Type Classification in a Fighter Flight Simulator

Savaş Uçağı Uçuş Simülatöründe EEG Tabanlı Görev Türü Sınıflandırması İçin Elektrot ve Frekans Bandı Öneminin İncelenmesi

Mustafa Şen(BANDIRMA ONYEDI EYLUL UNIVERSITY)0000-0003-3008-7656
İlyas Özer(BANDIRMA ONYEDI EYLUL UNIVERSITY)0000-0003-2112-5497
Adem Dalcalı(BANDIRMA ONYEDİ EYLÜL ÜNİVERSİTESİ, MÜHENDİSLİK VE DOĞA BİLİMLERİ FAKÜLTESİ)0000-0002-9940-0471
Pages
—
Publication Date
2026-07-09
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings support the development of lightweight wearable EEG systems for mission-type recognition in aviation neuroergonomics.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Electroencephalography (EEG) is increasingly used in neuroergonomics to monitor pi-lot states during complex flight operations; however, the frequency bands and scalp regions most informative for distinguishing operationally relevant mission types re-main unclear.
📊
Key Findings & Data:This study analyzed a 16-channel EEG dataset recorded from seven ex-perienced fighter pilots during three high-fidelity F-16 simulator missions: an air-to-ground strike under air-defense threat, an air-to-air beyond-visual-range en-gagement, and an air-to-air close-range dogfight.
💡
Conclusion & Impact:These findings support the development of lightweight wearable EEG systems for mission-type recognition in aviation neuroergonomics.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Electroencephalography · flight simulator · mission classification

Abstract

Electroencephalography (EEG) is increasingly used in neuroergonomics to monitor pi-lot states during complex flight operations; however, the frequency bands and scalp regions most informative for distinguishing operationally relevant mission types re-main unclear. This study analyzed a 16-channel EEG dataset recorded from seven ex-perienced fighter pilots during three high-fidelity F-16 simulator missions: an air-to-ground strike under air-defense threat, an air-to-air beyond-visual-range en-gagement, and an air-to-air close-range dogfight. Subject-independent binary classifi-cation of air-to-ground versus air-to-air missions was performed by grouping both air-to-air scenarios and applying a filterbank Riemannian processing framework with leave-one-pilot-out cross-validation. The baseline model, using five bands and all elec-trodes, achieved 89.3% run-level balanced accuracy and 88.0% macro-F1, with 100% sensitivity for air-to-air and 78.6% specificity for air-to-ground missions. Band-ablation analyses showed that theta-only and theta+alpha configurations yielded the highest balanced accuracy (96.4%), followed by alpha-only (94.6%), whereas beta and low-gamma bands performed comparatively lower. Electrode permutation and channel-subset analyses further indicated that a 12-channel parieto-frontal montage matched or improved performance, while a compact four-channel subset preserved baseline accuracy. These findings support the development of lightweight wearable EEG systems for mission-type recognition in aviation neuroergonomics.

Özet

Elektroensefalografi (EEG), karmaşık uçuş operasyonları sırasında pilot durumlarını izlemek amacıyla nöroergonomi alanında giderek daha fazla kullanılmaktadır; ancak operasyonel açıdan anlamlı görev türlerini ayırt etmede en bilgilendirici frekans bantları ve kafa derisi bölgeleri hâlen net değildir. Bu çalışmada, yedi deneyimli savaş uçağı pilotundan üç yüksek gerçeklikli F-16 simülatör görevi sırasında kaydedilen 16 kanallı bir EEG veri seti analiz edilmiştir: hava savunma tehdidi altında bir hava-yer taarruz görevi, görüş ötesi menzilde bir hava-hava angajmanı ve yakın mesafe hava-hava it dalaşı. Hava-yer ve hava-hava görevlerinin denekten bağımsız ikili sınıflandırması, her iki hava-hava senaryosu gruplanarak ve bir pilot dışarıda bırakmalı çapraz doğrulama ile filtre bankası Riemannian işleme çerçevesi uygulanarak gerçekleştirilmiştir. Beş bant ve tüm elektrotları kullanan temel model, görev koşusu düzeyinde %89,3 dengeli doğruluk ve %88,0 makro-F1 değerine ulaşmış; hava-hava görevleri için %100 duyarlılık ve hava-yer görevleri için %78,6 özgüllük elde etmiştir. Bant çıkarma analizleri, yalnızca teta ve teta+alfa yapılandırmalarının en yüksek dengeli doğruluğu (%96,4) sağladığını, bunu yalnızca alfa yapılandırmasının (%94,6) izlediğini; beta ve düşük gama bantlarının ise görece daha düşük performans gösterdiğini ortaya koymuştur. Elektrot permütasyonu ve kanal alt kümesi analizleri ayrıca, 12 kanallı pariyeto-frontal montajın performansı temel modelle eşleştirdiğini veya iyileştirdiğini, kompakt dört kanallı bir alt kümenin ise temel doğruluğu koruduğunu göstermiştir. Bu bulgular, havacılık nöroergonomisinde görev türü tanıma amacıyla hafif giyilebilir EEG sistemlerinin geliştirilmesini desteklemektedir.

🔖

Cite This Article

Şen, M., Özer, İ., Dalcalı, A., *, A. D. (2026). Electrode and Frequency Band Importance for EEG-Based Mission-Type Classification in a Fighter Flight Simulator. Electronic Letters on Science and Engineering, Volume: 22 Issue: 1. https://ajindex.com/articles/1180940

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (23)

  1. Parasuraman, R. Neuroergonomics: research and practice. Theor. Issues Ergon. Sci. 2003, 4(1-2), 5-20.
  2. Mehta, R.K.; Parasuraman, R. Neuroergonomics: A review of applications to physical and cognitive work. Front. Hum. Neurosci. 2013, 7.
  3. Belkhiria, C.; Peysakhovich, V. Electro-encephalography and electro-oculography in aeronautics: A review over the last decade (2010–2020). Front. Neuroergon. 2020, 1, 606719.
  4. Luzzani, G.; Buraioli, I.; Demarchi, D.; Guglieri, G. A review of physiological measures for mental workload assessment in aviation: A state-of-the-art review of mental workload physiological assessment methods in human-machine interaction analysis. Aeronaut. J. 2024, 128(1323), 928–949.
  5. Dehais, F.; Dupres, A.; Blum, S.; Drougard, N.; Scannella, S.; Roy, R.N.; Lotte, F. Monitoring pilot’s mental workload using ERPs and spectral power with a six-dry-electrode EEG system in real flight conditions. Sensors 2019, 19(6), 1324.
  6. Mohanavelu, K.; Poonguzhali, S.; Adalarasu, K.; Ravi, D.; Vijayakumar, C.; Vinutha, S.; Ramachandran, K.; Srinivasan, J. Dynamic cognitive workload assessment for fighter pilots in a simulated fighter aircraft environment using EEG. Biomed. Signal Process. Control 2020, 61, 102018.
  7. Gorji, H.T.; Wilson, N.; VanBree, J.; Hoffmann, B.; Petros, T.; Tavakolian, K. Using machine learning methods and EEG to discriminate aircraft pilot cognitive workload during flight. Sci. Rep. 2023, 13, 2507.
  8. Hernández-Sabaté, A.; Yauri, J.; Folch, P.; Alvarez, D.; Gil, D. EEG dataset collection for mental workload predictions in flight-deck environment. Sensors 2024, 24(4), 1174.
  9. Barachant, A.; Bonnet, S.; Congedo, M.; Jutten, C. Riemannian geometry applied to BCI classification. In Proceedings of the 9th International Conference on Latent Variable Analysis and Signal Separation, Saint-Malo, France, 27–30 September 2010; pp. 629–636.
  10. Barachant, A.; Bonnet, S.; Congedo, M.; Jutten, C. Multiclass brain–computer interface classification by Riemannian geometry. IEEE Trans. Biomed. Eng. 2012, 59(4), 920–928.
  11. Congedo, M.; Barachant, A.; Andreev, A. A new generation of brain–computer interface based on Riemannian geometry. arXiv 2013, arXiv:1310.8115.
  12. Yger, F.; Berar, M.; Lotte, F. Riemannian approaches in brain–computer interfaces: A review. IEEE Trans. Neural Syst. Rehabil. Eng. 2017, 25(10), 1753–1762.
  13. Tibermacine, I.E.; Russo, S.; Tibermacine, A.; Rabehi, A.; Nail, B.; Kadri, K.; Napoli, C. Riemannian geometry-based EEG approaches: A literature review. arXiv 2024, arXiv:2407.20250.
  14. Kalunga, E.K.; Chevallier, S.; Barthélemy, Q.; Djouani, K.; Monacelli, E.; Hamam, Y. Online SSVEP-based BCI using Rie-mannian geometry. Neurocomputing 2016, 191, 55–68.
  15. Wu, D.; Lance, B.J.; Lawhern, V.J.; Gordon, S.; Jung, T.P.; Lin, C.T. EEG-based user reaction time estimation using Riemannian geometry features. IEEE Trans. Neural Syst. Rehabil. Eng. 2017, 25(11), 2157–2168.
  16. He, H.; Wu, D. Transfer learning for brain–computer interfaces: A Euclidean space data alignment approach. IEEE Trans. Biomed. Eng. 2020, 67(2), 399–410.
  17. He, H.; Wu, D. Spatial filtering for brain–computer interfaces: A comparison between the common spatial pattern and its variant. In Proceedings of the IEEE International Conference on Signal Processing, Communications and Computing, China, 2018.
  18. Lotte, F.; Bougrain, L.; Cichocki, A.; Clerc, M.; Congedo, M.; Rakotomamonjy, A.; Yger, F. A review of classification algorithms for EEG-based brain–computer interfaces: A 10-year update. J. Neural Eng. 2018, 15(3), 031005.
  19. Brodu, N.; Lotte, F.; Lécuyer, A. Exploring two novel features for EEG-based brain–computer interfaces: Multifractal cumulants and predictive complexity. Neurocomputing 2012, 79(1), 87–94.
  20. Tan, C.; Sun, F.; Zhang, W.; Chen, J.; Liu, C. Multimodal classification with deep convolutional–recurrent neural networks for electroencephalography. In Proceedings of the International Conference on Neural Information Processing, 2017; pp. 767–776.
  21. Ivanov, N.; Chau, T. Riemannian geometry-based metrics to measure and reinforce user performance changes during brain–computer interface user training. Front. Comput. Neurosci. 2023, 17.
  22. Roy, R.N.; Bonnet, S.; Charbonnier, S.; Campagne, A. Efficient workload classification based on ignored auditory probes: A proof of concept. Front. Hum. Neurosci. 2016, 10.
  23. Tang, S.; Liu, C.; Zhang, Q.; Gu, H.; Li, X.; Li, Z. Mental workload classification based on ignored auditory probes and spatial covariance. J. Neural Eng. 2021, 18(4).