Welcome to Francis Academic Press
Login | Register

International Journal of New Developments in Engineering and Society, 2024, 8(5); doi: 10.25236/IJNDES.2024.080508.

Data Analysis and Model Construction for Crew Fatigue Monitoring Based on Machine Learning Algorithms

Author(s)

Boyang Liu

Corresponding Author:
Boyang Liu
Affiliation(s)

Operation Department, ONUS Global Fulfilment Solutions, Richmond, V6W 1G3, British Columbia, Canada

Abstract

This article aims to study the construction method of a crew fatigue monitoring and analysis system based on machine learning algorithms, with a focus on addressing the limitations of existing systems in fatigue recognition and prediction. This article by analysing the workload and fatigue characteristics of crew members, this paper designs a dynamic model driven by multidimensional data to accurately identify and predict fatigue states. This research system combines deep learning technology and improves data processing efficiency and monitoring accuracy through multi-source data fusion and adaptive modeling. This model has real-time optimization capability and can automatically adjust parameters based on individual differences in crew members and working conditions to achieve personalized fatigue management. The system we are researching can effectively reduce safety hazards caused by crew fatigue, thereby providing reliable technical support for the long-term health of crew members.

Keywords

Machine Learning Algorithms, Crew Fatigue Monitoring, Multidimensional Data Fusion, Dynamic Models, Deep Learning

Cite This Paper

Boyang Liu. Data Analysis and Model Construction for Crew Fatigue Monitoring Based on Machine Learning Algorithms. International Journal of New Developments in Engineering and Society (2024) Vol.8, Issue 5: 48-52. https://doi.org/10.25236/IJNDES.2024.080508.

References

[1] Myers R. Flight Crew Fatigue And Controlled Rest Management System: EP20220150826 [P]. EP4030394A1 [2024-09-13].

[2] Sun J, Sun R, Li J, et al. Flight crew fatigue risk assessment for international flights under the COVID-19 outbreak response exemption policy[J]. BMC Public Health, 2022, 22(1):1-20. DOI: 10.1186/s12889-022-14214-5.

[3] Olbert A, Klemets T. An Comprehensive Investigation of Regulatory Flight and Duty Time Limitation and their Ability to Control Crew Fatigue [J]. IEEE, 2022.

[4] Shafiee M, Adedipe T. A Bayesian network model for the probabilistic safety assessment of offshore wind decommissioning[J]. Wind Engineering, 2023, 47(1):104-125.

[5] Philippe K, Paillard T, Maurelli O, et al. Effects of an Offshore Sailing Competition on Anthropometry, Muscular Performance, Subjective Wellness, and Salivary Cortisol in Professional Sailors [J]. International journal of sports physiology and performance, 2022, 17(8):1205-1212. DOI:10.1123/ijspp.2021-0575.

[6] Mansyur M, Sagitasari R, Wangge G, et al. Long working hours, poor sleep quality, and work-family conflict: determinant factors of fatigue among Indonesian tugboat crewmembers [J]. BioMed Central, 2021(1). DOI:10.1186/S12889-021-11883-6.

[7] José A. Orosa. Application of Machine Learning in the Identification and Prediction of Maritime Accident Factors[J]. Applied Sciences, 2024, 14. DOI:10.3390/app14167239.

[8] Roma P, Jameson J T, Kubala A, et al. Sleep, Team and Social Processes, and Health, Performance, and Safety in Naval Operational Environments[J]. Sleep, 2022. DOI:10.1093/sleep/ zsac 079.003.