Application of Random Forest and HRV Analysis for Real-Time Pilot Mental Workload Monitoring: Toward an Intelligent Cockpit Support System
Carmelo Rosario VINDIGNI, Giuseppe IACOLINO, Antonio ESPOSITO, Calogero ORLANDO, Andrea ALAIMO
Abstract. In aviation, continuous monitoring of pilots’ mental workload is vital to ensure safety and performance, as cognitive overload or underload can affect decision-making and situational awareness. This study explores the use of heart rate variability, a physiological marker linked to mental effort, for real-time MW assessment using wearable bio-sensors. A Random Forest machine learning algorithm is applied to classify workload levels, exploiting its robustness, interpretability, and ability to model complex feature interactions. The study evaluates RF performance across different settings to find the best configuration for the development of an embedded cockpit support system. Results are evaluated against a Kriging model to assess comparative effectiveness.
Keywords
Mental Workload Monitoring, Heart Rate Variability, Random Forest Classification, Aviation Human Factors
Published online 7/20/2026, 4 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Carmelo Rosario VINDIGNI, Giuseppe IACOLINO, Antonio ESPOSITO, Calogero ORLANDO, Andrea ALAIMO, Application of Random Forest and HRV Analysis for Real-Time Pilot Mental Workload Monitoring: Toward an Intelligent Cockpit Support System, Materials Research Proceedings, Vol. 69, pp 1456-1459, 2026
DOI: https://doi.org/10.21741/9781644904251-255
The article was published as article 255 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] G. Iacolino, A. Esposito, C. Orlando, and A. Alaimo, “A brief review of pilots’ workload assessment using flight simulators: subjective and objective metrics,” Materials Research Proceedings, vol. 37, 2023. https://doi.org/10.21741/9781644902813-161
[2] L. Breiman, “Random forests,” Machine learning, vol. 45, no. 1, pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324
[3] A. Esposito, G. Iacolino, C. Orlando, and A. Alaimo, “Metamodelling of the workload assessment in simulated flights using the kriging method,” in ICAS Proceedings, 2024.
[4] A. Rajendran, P. M. Kebria, N. Mohajer, A. Khosravi, and S. Nahavandi, “Machine learning based prediction of situational awareness in pilots using ecg signals,” in 2021 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1-6, IEEE, 2021. https://doi.org/10.1109/SSCI50451.2021.9660076
[5] H. Taheri Gorji, N. Wilson, J. VanBree, B. Hoffmann, T. Petros, and K. Tavakolian, “Using machine learning methods and eeg to discriminate aircraft pilot cognitive workload during flight,” Scientific Reports, vol. 13, no. 1, p. 2507, 2023. https://doi.org/10.1038/s41598-023-29647-0
[6] C. Liu, C. Zhang, L. Sun, K. Liu, H. Liu, W. Zhu, and C. Jiang, “Detection of pilot’s mental workload using a wireless eeg headset in airfield traffic pattern tasks,” Entropy, vol. 25, no. 7, p. 1035, 2023. https://doi.org/10.3390/e25071035
[7] P. Wang, R. Houghton, and A. Majumdar, “Detecting and predicting pilot mental workload using heart rate variability: a systematic review,” Sensors, vol. 24, no. 12, p. 3723, 2024. https://doi.org/10.3390/s24123723
[8] T. Wong, “Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation,” Pattern recognition, vol. 48, no. 9, pp. 2839-2846, 2015. https://doi.org/10.1016/j.patcog.2015.03.009
[9] G. Naidu, T. Zuva, and E. M. Sibanda, “A review of evaluation metrics in machine learning algorithms,” in Computer science on-line conference, pp. 15-25, Springer, 2023. https://doi.org/10.1007/978-3-031-35314-7_2
