DYNAMIC MODEL FOR CALCULATING NAVIGATOR FATIGUE LEVEL – PREDICTIVE FATIGUE INDEX
https://doi.org/10.33815/2313-4763.2025.2.31.199-208
Abstract
The research addresses the challenges of assessing the human factor in maritime navigation, with a particular focus on the fatigue and cognitive workload of ship navigators during the operation of Electronic Chart Display and Information Systems (ECDIS). The study provides a comprehensive review and critical analysis of current approaches and mathematical models, including NASA-TLX, SWAT, HFACS, and SAFTE, highlighting their strengths and limitations in predicting operator errors and identifying high-risk situations. A new integrative indicator is proposed: the Psychophysical Fatigue Index (PFI), which quantitatively assesses physiological fatigue while taking into account cognitive load arising from physiological, operational, and contextual factors. The model introduces dynamic adjustment of weighting coefficients using machine learning techniques, allowing for adaptive, individual-specific calibration. Contextual parameters such as weather conditions, traffic density, time of day, and complexity of the navigation route are integrated into the model to enhance predictive accuracy. PFI operates in two modes—operational and stationary—providing both real-time monitoring and baseline assessments of the navigator’s state. In addition, the research presents a multidimensional metric that evaluates cognitive workload by integrating physiological signals, operational tasks, and contextual influences to provide a holistic assessment of navigator performance. The proposed models can be implemented in navigation bridge systems and training simulators for the early detection of elevated fatigue levels and cognitive overload, thereby contributing to risk reduction and improved maritime safety. A comparative analysis of existing models and the proposed integrative approach demonstrates improved accuracy in error risk prediction, optimized watch scheduling, and enhanced decision support. Prospects for future research include further development of adaptive machine learning algorithms for individualized assessments, integration of multidimensional real-time data, and validation through operational and simulator-based studies, aiming for a comprehensive evaluation of the navigator’s physical and cognitive state under varying operational conditions.
References
URL: https://www.emsa.europa.eu/publications/download/8329/5562/23.html.
2. Asanka Rajapakse, Gholam Reza Emad (2023). Fatigue, an unsolved puzzle that continues contributing to accidents at sea, Marine Policy, Volume 155, 105745, ISSN 0308-597X, https://doi.org/10.1016/j.marpol.2023.105745.
3. Maternová, A., Materna, M., Dávid, A., Török, A., Švábová, L. (2023). Human Error Analysis and Fatality Prediction in Maritime Accidents. J. Mar. Sci. Eng.,11, 2287. https://doi.org/10.3390/jmse11122287.
4. Vojkovi´c, L., Bakota, M., Kuzmani´c Skelin, A. (2024). Using the Bayes Probability Model to Evaluate the Risk of Accidents Caused by the Electronic Chart Display and Information System J. Mar. Sci. Eng., 12(8), 391; https://doi.org/10.3390/jmse12081391.
5. Gizem Kayisoglu, Pelin Bolat and Kimberly Tam (2022). Evaluating SLIM-based human error probability for ECDIS cybersecurity in maritime. The Journal of Navigation, 75:6 1364–1388, doi:10.1017/S0373463322000534.
6. Liu Yang, Luyao Li, Qing Liu, Yue Ma, Junsong Liao (2023). Influence of physiological, psychological and environmental factors on passenger ship seafarer fatigue in real navigation environment, Safety Science, Volume 168, 106293, ISSN 0925–7535, https://doi.org/10.1016/j.ssci.2023.106293.
7. Christine Chauvin, Salim Lardjane, Gaël Morel, Jean-Pierre Clostermann, Benoît Langard (2013). Human and organisational factors in maritime accidents: Analysis of collisions at sea using the HFACS, Accident Analysis & Prevention, Volume 59, Pages 26–37, ISSN 0001-4575, https://doi.org/10.1016/j.aap.2013.05.006.
8. Laihao Ma, Xiaoxue Ma, Ting Wang, Liguang Chen, He Lan (2024). On the development and measurement of human factors complex network for maritime accidents: A case of ship groundings, Ocean & Coastal Management, Volume 248, 106954, ISSN 0964-5691, https://doi.org/10.1016/j.ocecoaman.2023.106954.
9. Nosov, P. S., Ben, A. P., Matejchuk, V. N., Safonov, M. S. (2018). «IDENTIFICATION OF “HUMAN ERROR” NEGATIVE MANIFESTATION IN MARITIME TRANSPORT». Radio Electronics, Computer Science, Control, 2018 (№ 4). P. 204–213, https://doi.org/10.15588/1607-3274-2018-4-20.
10. Nosov, P. S., Cherniavskyi, V. V., Zinchenko, S. M., Popovych, I. S., Nahrybelnyi, Ya. А., Nosova, H. V. (2021). «IDENTIFICATION OF MARINE EMERGENCY RESPONSE OF ELECTRONIC NAVIGATION OPERATOR». Radio Electronics, Computer Science, Control, (№ 1), P. 208–223, https://doi.org/10.15588/1607-3274-2021-1-20.
11. Žagar, D., Svetina, M., Košir, A., Dimc, F. (2020). «Human Factor in Navigation: Overview of Cognitive Load Measurement during Simulated Navigational Tasks». Journal of Marine Science and Engineering, 8(10), 775, P. 1–11. https://doi.org/10.3390/jmse8100775.
12. Article «Human Factors and Maritime Safety» – Christine Chauvin. The Journal of Navigation, (2011), 64(4), 625–632 https://doi.org/https://doi.org/10.1017/S0373463311000142.
13. Shiqi Fan, Zaili Yang (2023). Towards objective human performance measurement for maritime safety: A new psychophysiological data-driven machine learning method, Reliability Еngineering & System Safety, Volume 233, 109103, ISSN 0951-8320, https://doi.org/10.1016/j.ress.2023.109103.
14. Manuel Vázquez Neira, Genaro Cao Feijóo, Blanca Sánchez Fernández and José A. Orosa (2025). Deep Learning for Visual Leading of Ships: AI for Human Factor Accident Prevention Appl. Sci., 15(15), 8261; https://doi.org/10.3390/app15158261.
15. Brit-Eli Danielsen, Margareta Lützhöft, Torgeir Kolstø Haavik, Stig Ole Johnsen, Thomas Porathe (2022). “Seafarers should be navigating by the stars”: barriers to usability in ship bridge design, Cognition Technology and Work, 24(4):1–17, P. 675–691, https://doi.org/10.1007/s10111-022-00700-8.
