近年來醫療業對於服務的品質越來越加重視，醫院不僅需具備優越的醫療技術及設備，而能否提供更貼心的醫療服務，往往是病患選擇求診醫院的關鍵。因此，醫院無不竭盡所能的提升醫療服務品質，應用工業工程與科學管理的方法妥善的規劃醫療資源，進而加強對病患的醫療服務。除了卓越的醫療技術外，完善的醫療服務，將成為醫院的競爭力核心，也是目前醫院經營的重要課題。
本研究目的為應用科學管理的方法於醫療服務的範疇，針對物理復健排程問題，建構學習法則訓練模式進行求解。物理復健排程問題屬於混合式的排程問題，研究中將應用屬性歸納的方法去擷取基因演算法的資料樣型，從中進行樣型的分析，建構學習法則的歸納模式，最後推導出學習法則，本研究希望藉由學習法則的便於應用、快速求解的優點，應用於物理復健排程問題的求解，將更有效率的進行排程規劃。最後本研究應用新竹某一教學醫院復健部門之歷史資料進行實證，應用屬性歸納方法推導出學習法則，並進行復健排程的規劃。經由實驗結果可知本研究可在較短的時間且節省運算成本的情況下，得到可行的排程規劃，在此適當的求解品質下，可改善物理復健部門之資源規劃效率。

Besides excellent medical techniques, perfect service has became the core competence. The hospitals emphasize service quality than ever recently. Providing considerable medical service is more important than advanced medical equipments. Hospitals do the best to improve service quality that is always the key factor to choice the hospital. The engineers can also use scientific methods to find proper resource distribution and enhance the service quality.
This research use scientific methods to construct the learning rules for physical therapy scheduling problem. This study use attribute oriented induction methods to extract the pattern based on GA methods and construct the potential rules in therapy scheduling problem. This method provides the advantages of efficiency and near optimal solution on GA. Finally, we have a numerical illustration in physical therapy scheduling problem based on results from proposed learning rules. And the experimental results show that proposed methods can improve the efficiency and cost to find the near optimal solution in such scheduling problem.

【1】曾繁斌, “醫院復健排程模式與演算法之研究”, 國立清華大
學工業工程與工程管理學系碩士論文，2003.
【2】彭文正譯, 資料挖礦顧客關係管理暨電子行銷之管理，維科，
2001
【3】Hamilton, D. M., and Breslawski, S. (1996),
“Knowledge Acquisition for Multiple Site, Relate
Domain Expert System: Delphi Process and
Application”, Expert Systems With Applications,
Vol.11, No.3, pp. 377-389.
【4】Marinagi, C. C., Spyropoulosa, C. D., Papatheodorou,
C., and Kokkotos, S. (2000), “Continual planning and
scheduling for managing patient tests in hospital l
laboratories”, Artificial Intelligence in Medicine,
Vol. 20, pp. 139-154.
【5】Focke A. and Christian S.(2003), “Strategic
technology planning in hospital management”, OR
Spectrum, pp. 161-182.
【6】Kim, S., Horowitz I., Young K. K., and Buckley T. A.
(2000), “Flexible bed allocation and performance in
the intensive care unit”, Journal of Operations
Management, Vol.18, pp. 427-443.
【7】Farrington, P. A., Nembherd, H. B., and Evans, G. W.
(1999), “Determination of operation room requirement
using simulation”, Proceedings of the 1999 Winter
Simulation Conference, pp. 1568-1572.
【8】Centeno, M. A., Albacete, C., Terzano, D. O.,
Carrillo, M., and Ogazon, T. (2000), “A simulation
study of the radiology department at JMH”,
Proceedings of the 2000 Winter Simulation Conference,
pp. 1978-1984.
【9】Ramudhin, A., and Marrier, P. (1996), “The
Generalized Shifting Bottleneck Procedure”, European
Journal of Operational Research, Vol.93, pp. 34-48.
【10】Baesler, F. F., and Sepúlveda, J. A. (2001), “Multi-
Objective simulation optimization for a cancer
treatment center”, Proceedings of the 2001 Winter
Simulation Conference, pp. 1405-1411.
【11】Millar, H. H., and Kiragu, M. (1998), “Cyclic and
non-cyclic scheduling of 12 h shift nurses by network
programming”, European Journal of Operational
Research, Vol.104, pp. 582-592.
【12】Valouxis, C., and Housos, E. (2000), “Hybrid
optimization techniques for the workshift and rest
assignment of nursing personnel”, Artificial
Intelligence in Medicine, Vol.20, pp. 155-175.
【13】Dowsland K. A.(1998), “Nurse scheduling with tabu
search and strategic oscillation”, European Journal
of Operational Research, Vol.106, pp. 393-407.
【14】Lee, K. M., Yamakawa, T., and Lee, K. M. (1998), “A
Genetic Algorithm for General Machine Scheduling
Problems”, Proceedings of the 1998 IEEE Second
International Conference on Knowledge-Based
Intelligent Electronic Systems, Vol. 2, pp. 60-66.
【15】Goldberg, D. (1989), Genetic Algorithms in Search,
Optimization and Machine Learning, Addison-Wesley, MA.
【16】Gen, M., and Cheng, R. (1997), Genetic Algorithms &
Engineering Design, John Wiley & Sons, New York.
【17】Cai, Y., Cercone, N., & Han, J. (1991).Attribute-
oriented Induction in relational databases, Knowledge
Discovery in Databases. Cambridge, MA：MIT Press.
【18】Genesereth, M., and Nilsion, N. 1987. Logical
Foundations of Artificial Intelligence. San Mateo,
Calif.: Morgan Kaufmann.
【19】Michalski, R. S. 1983. A Theory and Methodology of
Inductive Learning. In Machine Learning: An
Artificial Intelligence Approach, Vol.1, 83-134. San
Mateo, Calif.: Morgan Kaufmann.
【20】Han, J., & Fu, Y.(1996). Attribute-oriented induction
in data mining, Advances in Knowledge Discovery and
Data Mining. Cambridge, MA: T Press.