METHOD OF AUTOMATED IDENTIFICATION OF HAZARDOUS FATIGUE FACTORS IN NAVIGATORS BASED ON SLEEP INDICATORS
https://doi.org/10.33815/2313-4763.2024.1.28.006-021
Abstract
The issue of fatigue among navigators during the performance of their duties poses a significant risk to maritime safety, with human factors being the primary cause of marine accidents. The aim of this study is to develop and test an automated method for identifying hazardous fatigue factors in navigators based on sleep indicators. This study addresses the challenge of accurately diagnosing fatigue, which is often underestimated or misinterpreted by the navigators themselves. The research involved long-term monitoring of the psychophysiological state of navigators during their duties and rest periods on the vessels "Alexander" IMO 9433353, "Brigitte M" IMO 9155913, and "LONGWOOD" IMO 9504138. Various statistical and dynamic analysis methods were used in the study, including regression analysis, time series analysis, and Student's t-test.
The experiments demonstrated a significant correlation between the duration of deep sleep and the reduction in wakefulness periods, indicating that longer periods of deep sleep mitigate the effects of fatigue. It was established that an increase in deep sleep time by 1% leads to a decrease in wakefulness time by an average of 0.736% to 0.98%. The correlation coefficient between deep sleep duration and stress level ranged from 0.73 to 0.98, confirming a high degree of correlation. The approximation error values ranged from 0.34% to 12.44%, indicating satisfactory model quality.
The developed automated system for fatigue detection showed promising results in enhancing navigational safety by providing real-time analysis and adaptive watch scheduling based on crew condition. The system is capable of automatically adjusting watch schedules and rest periods, ensuring an optimal balance between workload and rest. The practical significance of the system lies in its potential to reduce the impact of the human factor on maritime safety by 18-28% and optimize voyage time, contributing to fuel and energy savings. The system can also automatically intervene in cases of critical decreases in navigator performance, for example, by automatically switching to auxiliary control systems (autopilot) or sending alarm signals to other crew members or the control center.
The theoretical significance of the obtained results lies in the experimental proof of the effectiveness of using sleep indicators for real-time monitoring and analysis of navigator fatigue. The practical significance of the results lies in the development of a system that ensures timely detection of hazardous navigator states, reduces the risk of accidents, and enhances overall navigational safety.
References
2. Zhang, Daiyong & Chu, Xiumin & Liu, Chenguang & He, Zhibo & Zhang, Pulin & Wu, Wenxiang (2024). A Review on Motion Prediction for Intelligent Ship Navigation. Journal of Marine Science and Engineering. 12. 107. 10.3390/jmse12010107.
3. Guo, Jian & Guo, Hua (2023). Real-Time Risk Detection Method and Protection Strategy for Intelligent Ship Network Security Based on Cloud Computing. Symmetry. 15. 988. 10.3390/sym15050988.
4. Nosov, P., Zinchenko, S., Ben, A., Prokopchuk, Y., Mamenko, P., Popovych, I., Moiseienko, V., Kruglyj, D. (2021). Navigation safety control system development through navigator action prediction by Data mining means. Eastern-European Journal of Enterprise Technolo-gies, 2 (9 (110)), 55–68. doi: https://doi.org/10.15587/1729-4061.2021.229237.
5. Nosov, P., Koretsky, O., Zinchenko, S., Prokopchuk, Y., Gritsuk, I., Sokol, I., Kyrychenko, K. (2023). Devising an approach to safety management of vessel control through the identification of navigator’s state. Eastern-European Journal 1of Enterprise Technologies, 4 (3 (124)), 19–32. doi: https://doi.org/10.15587/1729-4061.2023.286156.
6. Чала Ю. М., Шахрайчук А. М. (2018). Психодіагностика: навчальний посібник / Ю. М. Чала, А. М. Шахрайчук. Харків: НТУ «ХПІ».
7. Ma, Xiaoxue & Shen, Jun & Liu, Yang & Qiao, Weiliang (2020). A Methodology to Evaluate the Effectiveness of Intelligent Ship Navigational Information Monitoring System. IEEE Access. 8. 10.1109/ACCESS.2020.3032543.
8. Психологія стресу та стресових розладів (2023): навч. посіб. / П86 Уклад. О. Ю. Овчаренко. К.: Університет «Україна». 266 с. ISBN 978-966-388-665-7.
9. HANDBOOK OF PSYCHOPHYSIOLOGY/John T. Cacioppo University of Chicago Louis G. Tassinary TexasA&M University Gary G. Berntson/ Cambridge University Press 2007.
10. Solovey, O., Ben, A., Dudchenko, S., Nosov, P. (2020). Development of control model for loading operations on Heavy Lift vessels based on inverse algorithm. Eastern European Journal of Enterprise Technologies, 5/2 (107), 48–56. https://doi.org/10.15587/1729-4061.2020.214856.
11. ІМО GUIDANCE ON FATIGUE MITIGATION AND MANAGEMENT 12 June 2001.
12. The Sleep Solution WHY YOUR SLEEP IS BROKEN AND HOW TO FIX IT By W. CHRIS WINTER, M.D. 4 April 2017, Penguin Random House.
13. Xinyi, Wang (2024). The applications and prospects of intelligent services robots in medicine. Applied and Computational Engineering. 35. 104–109. 10.54254/2755-2721/35/20230375.
14. Amana, Anthony & Ngang Bassey Ph.D., Engr.Dr.Ngang (2021). Intelligent agent based-Real time monitoring and Evaluation of GSM quality of service. Journal of Information & Knowledge Management. 11. 35–49. 10.7176/IKM/11-4-05.
15. Ibrahim, & Syahputra, Hindra & Sugito, Bambang & Iqbal, Muhammad & Wijaya, Rian (2023). Optimizing Logistics System Monitoring with FIFO Method Using Intelligent System. International Journal Of Computer Sciences and Mathematics Engineering. 2. 276–280. 10.61306/ijecom.v2i2.53.
16. Dohare, Sushil & K, Deeba & Pamulaparthy, Laxmi & Abdufattokhov, Shokhjakhon & Venkata, Janjhyam & Ramesh, Janjhyam & El-Ebiary, Yousef & Thenmozhi, E. (2024). Enhancing Diabetes Management: A Hybrid Adaptive Machine Learning Approach for Intelligent Patient Monitoring in e-Health Systems. 10.14569/IJACSA.2024.0150162.
17. Wu, Zhong & She, Qiping & Zhou, Chuan (2024). Intelligent Customer Service System Optimization Based on Artificial Intelligence. Journal of Organizational and End User Computing. 36. 1–27. 10.4018/JOEUC.336923.
18. Zhang, Xinwei (2023). Innovative Applications of Image Media and Intelligent Service Systems. Scientific and Social Research. 5. 22–29. 10.26689/ssr.v5i12.5772.
19. Wang, Yanli (2022). Engineering Safety Management System Based on Robot Intelligent Monitoring. Advances in Multimedia. 1–10. 10.1155/2022/8940678.
20. Lin, Chin-Te & Lu, Hong-Ji (2024). An Intelligent Product-Driven Manufacturing System Using Data Distribution Service. IEEE Access. PP. 1–1. 10.1109/ACCESS.2024.3359228.
21. Zhao, Yixin & Liu, Yanzhong & Zhou, Haiyang & Wei, Yuxuan & Yu, Yansuo & Lu, Sichao & An, Xiang & Liu, Qiang (2023). Intelligent Gateway Based Human Cardiopulmonary Health Monitoring System. Journal of Sensors. 1–16. 10.1155/2023/3534224.
22. Holub, Halyna & Voronko, Iryna & Azizov, Borys & Chernenko, Vitalii & Moseichuk, Mykola & Ishchenko, Vitalii (2023). Analytical aspects of application of intelligent methods of management of computer systems in transport infrastructure projects. Technology audit and production reserves. 3. 25–29. 10.15587/2706-5448.2023.284578.
23. Zhao, Huadong & Sun, Shaoming (2023). Research on the Application of Intelligent Transportation System in Transportation Management. Academic Journal of Science and Technology. 4. 1–4. 10.54097/ajst.v4i2.3865.
24. Економетрія (2012). Ч. 1: навч. посібник / О. Волошин, Н. Галайко. Львів: Львівський державний університет внутрішніх справ. 192 с.
25. Економетрика (2015): навчальний посібник для студентів напряму підготовки "Економічна кібернетика" всіх форм навчання / Л. С. Гур'янова, Т. С. Клебанова, О. А. Сергієнко, С. В. Прокопович. Х. : ХНЕУ ім. С. Кузнеця. 384 с.
