AVIATION SPECIALIST FATIGUE ASSESSMENT BY THE RANDOM FOREST METHOD
https://doi.org/10.51955/2312-1327_2024_3_33
Abstract
The article examines the fatigue of flight personnel and members of the air traffic control service as a risk factor affecting flight safety. The proposed software solution based on the random forest method makes it possible to identify the state of fatigue in an aviation specialist after passing a series of tests evaluating a decrease in performance based on existing symptomatic attributes. The introduction of the presented solution into flight safety management systems at aviation enterprises will improve the corresponding reliability indicators of both pilots and air traffic controllers.
About the Author
D. A. Evsevichev
Ulyanovsk Institute of Civil Aviation named after Chief Marshal of Aviation B.P. Bugaev
Russian Federation
Russian Federation
Denis A. Evsevichev, Candidate of Technical Sciences, Associate Professor
Mozhayskogo street, 8/8 Ulyanovsk, 432071
References
1. Andronnikova E. A., Zaika E. V. (2011). Methods of perception, attention and memory research : A Guide for practical psychologists. Kharkov: Kharkov National University named by V. N. Karazin, 2011. 161 p. (In Russian)
2. Bukhtiyarov I. V., Yushkova O. I., Fesenko M. A., Merkulova A. G. (2018). Assessment of the risk of fatigue among workers of neuro-emotional labor. Health Risk Analysis. 1: 66-77. (In Russian) Bulatova A. E., Buzaeva E. A., Evsevichev D. A. (2023). Assessment of the state of fatigue of an aviation specialist using the decision tree method. Scientific bulletin of GosNII GA. 42: 49-58. (In Russian)
3. Chio K., Freeman D. (2020). Machine learning and security. Moscow: DMK Press, 2020. 388 p. (In Russian)
4. Doc 9966. Manual for the Oversight of Fatigue Management Approaches. Canada: ICAO, 2016. 195 p. (In Russian)
5. Enikeev R. V., Rybalkina A. L. (2020). Methodology for managing fatigue of engineering and technical personnel. XXI century: results of the past and problems of the present plus. 51: 132-137. (In Russian)
6. Ensembles: Gradient boosting, random forests, bagging, voting, stacking. Available at: https://scikit-learn.org/stable/modules/ensemble.html (accessed 05 March 2024).
7. Fatigue risk management system (FRMS) implementation guide for operators introduction. Canada: ICAO, 2011. 172 p.
8. Glassner A. (2019). Deep Learning: From Basics to Practice. Volume 1. Moscow: DMK Press, 2019. 584 p. (In Russian)
9. Jeron O. (2018). Applied machine learning using Scikit-Learn and TensorFlow: concepts, tools and techniques for creating intelligent systems. St. Petersburg: Alpha Book, 2018. 688 p. (In Russian) Muller A., Gvido S. (2017). An introduction to machine learning using Python. A guide for data professionals. Moscow: IC «Gevista», 2017. 393 p. (In Russian)
10. RandomForestClassifier – scikit-learn documentation (2024). Available at: https://scikitlearn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html (accessed 05 March 2024).
11. Sklearn.metrics.classification_report – scikit-learn documentation (2024). Available at: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html (accessed 05 March 2024).
12. Surina E.I. Labor and fatigue. What is the Fatigue Risk Management System (FRMS)? Available at: https://ppt-online.org/115414 (accessed 16 June 2024). (In Russian)
13. t-SNE in machine learning (2024). Available at: https://biconsult.ru/products/t-sne-v-mashinnomobuchenii (accessed 05 March 2024). (In Russian)
14. van der Maaten L., Hinton G. (2008). Visualizing Data using t-SNE. Journal of Machine Learning Research. 9: 2579-2605.
Review
For citations:
Evsevichev D.A. AVIATION SPECIALIST FATIGUE ASSESSMENT BY THE RANDOM FOREST METHOD. Crede Experto: transport, society, education, language. 2024;(3):33-44. (In Russ.) https://doi.org/10.51955/2312-1327_2024_3_33
Views:
9
JATS XML
Email this article 