運用蛙跳演算法解醫護人員排班問題

Applying a modified shuffled frog leaping algorithm to solve medical staff scheduling problems

10.6840/cycu201600480

洪梓誠

醫護人員排班 ； 醫護人員偏好 ； 人員排班 ； 蛙跳演算法 ； 穩健性 ； Medical staff scheduling ； medical staff preference ； staff scheduling ； shuffled frog leaping algorithm (SFLA) ； robustness

中原大學工業與系統工程學系學位論文

2016年

碩士

陳平舜

繁體中文

隨著人民注重醫療品質觀念的提升，近年來人民對於醫療需求的增加。再加上各家醫院的人力資源有限，導致每位醫護人員的工作負荷日益增加。醫院若未妥善規劃人力配置，容易造成醫療人員工作負荷過重，進而導致醫療品質惡化情況。因此，如何在符合政府及醫院法規的限制下，排出一個具有較受醫護人員滿意的班表已成為醫院管理的重大挑戰。 本研究發展一改良式蛙跳演算法求解醫護人員排班問題，並加入修復、更新和鄰域搜尋機制，以提升醫護人員班表之品質。而藉由圖形化介面的形式呈現最佳班表可方便醫院管理者使用醫護人員排班系統。另外，改良式蛙跳演算法在求解過程中展現不錯的收斂性，讓演算法可求得不錯的醫護人員班表，即滿足大部份的醫護人員排班偏好。最後，本研究透過穩健性分析，探討在不同班別人力分配下對於改良式蛙跳演算法所求班表之影響。其結果顯示，求解後之班表受到不同班別人力分配影響不大，即代表本研究發展之改良式蛙跳演算法具有高度的穩健性。

As people keep pursuing for better medical quality, medical demands of people increase in recent years. Due to limited medical staff of hospitals, each medical employee has more and more workload. If a hospital does not assign the appropriate staff to each shift, it will cause to over workload of each staff, leading to decrease medical quality. Therefore, how to arrange a medical staff schedule with high staff satisfaction to comply with government and hospital regulations becomes a significant challange for hospital management. This study developed a modified shuffled frog leaping algorithm (MSFLA) to solve the medical staff scheduling problem. Based on the MSFLA, this research designed the repairing, updating, and searching adjacent neighborhood mechanisms in order to improve solution quality of the medical staff schedule. Using the graphical user interface (GUI) to display an optimal schedule could help hospital managers conveniently access to the medical staff scheduling system. In addition, the results show that the MSFLA had a good convergence property, leading to a good medical staff schedule. In other words, the MSFLA could find a solution that satisfied most of staff’s preferences. Finally, this study conducted a robustness analysis in order to explore the impact of different required staff each shift on solution quality of the schedule generated by the proposed MSFLA. The numerical results show that, under different required staff each shift, solution quality of each replication was close. It meant that the proposed MSFLA had high robustness.

1. Bhattacharjee, K. K., & Sarmah, S. P. (2014). Shuffled frog leaping algorithm and its application to 0/1 knapsack problem. Applied Soft Computing, 19, 252-263.
   連結：
2. Burke, E. K., De Causmaecker, P., Vanden Berghe, G., & Van Landeghem, H. (2004). The state of the art of nurse rostering. Journal of Scheduling, 7(6), 441-499.
   連結：
3. Byars, L., & Rue, L. (1984). Human Resource and Personnel Management: McGraw-Hill/Irwin.
   連結：
4. Costa Filho, C. F. F., Rivera Rocha, D. A., Fernandes Costa, M. G., & de Albuquerque Pereira, W. C. (2012). Using constraint satisfaction problem approach to solve human resource allocation problems in cooperative health services. Expert Systems with Applications, 39(1), 385-394.
   連結：
5. Cui, W. H., Liu, X. B., Wang, W., & Wang, J. S. (2012). Survey on shuffled frog leaping algorithm. Control and Decision, 27, 481-486.
   連結：
6. Douglas Smith, L., & Wiggins, A. (1977). A computer-based nurse scheduling system. Computers & Operations Research, 4(3), 195-212.
   連結：
7. Eusuff, M. M., & Lansey, K. E. (2003). Optimization of water distribution network design using the shuffled frog leaping algorithm. Journal of Water Resources Planning and Management-ASCE, 129(3), 210-225.
   連結：
8. Gutjahr, W. J., & Rauner, M. S. (2007). An ACO algorithm for a dynamic regional nurse-scheduling problem in Austria. Computers & Operations Research, 34(3), 642-666.
   連結：
9. Ingels, J., & Maenhout, B. (2015). The impact of reserve duties on the robustness of a personnel shift roster: An empirical investigation. Computers & Operations Research, 61, 153-169.
   連結：
10. Lin, C. C., Kang, J. R., Chiang, D. J., & Chen, C. L. (2015). Nurse scheduling with joint normalized shift and day-off preference satisfaction using a genetic algorithm with immigrant scheme. International Journal of Distributed Sensor Networks, 11(7), Article ID 595419.
    連結：
11. Lin, C. C., Kang, J. R., Liu, W. Y., & Deng, D. J. (2014). Modelling a nurse shift schedule with multiple preference ranks for shifts and days-off. Mathematical Problems in Engineering, 2014, 10, Article ID 937842.
    連結：
12. Luo, J., Li, X., Chen, M. R., & Liu, H. (2015). A novel hybrid shuffled frog leaping algorithm for vehicle routing problem with time windows. Information Sciences, 316, 266-292.
    連結：
13. Niknam, T., & Azad Farsani, E. (2010). A hybrid self-adaptive particle swarm optimization and modified shuffled frog leaping algorithm for distribution feeder reconfiguration. Engineering Applications of Artificial Intelligence, 23(8), 1340-1349.
    連結：
14. Spyropoulos, C. D. (2000). AI planning and scheduling in the medical hospital environment. Artificial Intelligence in Medicine, 20(2), 101-111.
    連結：
15. Todorovic, N., & Petrovic, S. (2013). Bee colony optimization algorithm for nurse rostering. IEEE Transactions on Systems Man Cybernetics-Systems, 43(2), 467-473.
    連結：
16. Topaloglu, S., & Selim, H. (2010). Nurse scheduling using fuzzy modeling approach. Fuzzy Sets and Systems, 161(11), 1543-1563.
    連結：
17. Tsay, S. F., & Wang, H. H. (2007). Reflections on nursing education in Taiwan and its prospects from the perspective of nursing manpower policy. The Journal of Nursing, pp5-10.
    連結：
18. Wright, D., & Mahar, S. (2013). Centralized nurse scheduling to simultaneously improve schedule cost and nurse satisfaction. Omega, 41, 1042-1052.
    連結：
19. 徐子玲，建構一Web-Based護理排班支援系統，台北醫學大學醫學資訊研究所碩士論文，2002。
    連結：
20. 蔡嘉哲，運用萬用啟發式演算法解醫護人員排班問題，中原大學工業與系統工程學系碩士論文，2015。
    連結：
21. Ellis, J., Priest, M., MacPhee, M., & McCutcheon, A. S. (2006). Staffing for safety: A synthesis of the evidence on nurse staffing and patient safety. Canadian Health Services Research Foundation.