Heuristic and swarm intelligence algorithms for work-life balance problem

Gulmez, Esra; Koruca, Halil Ibrahim; Aydin, Mehmet Emin; Urganci, Kemal Burak

Abstract

Employee satisfaction significantly influences the success of business. This emphasises on the importance of employees managing their work, family and personal lives to maintain their physical and mental well-being. This is especially crucial in health-care sector, where physical and mental well-being directly affects the quality of out-coming services provided. Work-life balance, defined as the challenge of striking a reasonable equilibrium between work, family, and personal life, is gaining more attention. However, many studies do not adequately consider employee preferences when addressing this issue. This study introduces a mathematical model for work-life balance problem prioritising the worker preferences focusing on healthcare workers as a special case where personnel preferences are integrated into decision-making. The model has been comparatively solved with population-based algorithms for optimising weekly personnel schedules in order to make them more suitable for work-life balance. The population-based heuristic algorithms used for optimising the schedules are swarm intelligence algorithms; namely ant colony and particle swarm optimisation algorithms. The proposed approach allows the employees to opt their working hours and periods in the work-place, flexibly. We demonstrated with comparative analysis that the produced results with swarm intelligence algorithms evidently outperform one of the state-of-art works done with genetic algorithms, which proves the strength of the proposed problem solvers.

Citation

Gulmez, E., Koruca, H. I., Aydin, M. E., & Urganci, K. B. (2024). Heuristic and swarm intelligence algorithms for work-life balance problem. Computers and Industrial Engineering, 187, Article 109857. https://doi.org/10.1016/j.cie.2023.109857

• Journal Article Type: Article
• Acceptance Date: Dec 21, 2023
• Online Publication Date: Dec 23, 2023
• Publication Date: Jan 31, 2024
• Deposit Date: Dec 22, 2023
• Publicly Available Date: Jan 18, 2024
• Journal: Computers and Industrial Engineering
• Print ISSN: 0360-8352
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 187
• Article Number: 109857
• DOI: https://doi.org/10.1016/j.cie.2023.109857
• Public URL: https://uwe-repository.worktribe.com/output/11533996