軍事投資最適化比例之研究

The Optimization of Military Investment Ratios

陳勁甫(Ching-Pu Chen)；張正昌(Cheng-Chang Chang)；陳仁龍(Jen-Lung Chen)

軍事投資 ； 預算分配 ； 倒傳遞類神經網路 ； 基因遺傳演算法 ； Military Investment ； Budget Allocation ； Back-propagation Neural Network ； Genetic Algorithm

管理與系統

13卷3期（2006 / 07 / 01）

355 - 370

繁體中文

國防預算乃為一個國家達成其預定軍事戰略目標之量能，妥善規劃與運用有限之國防預算於各項軍事投資標的，將提升軍事作戰能力，進而確保國家安全。有關預算配置之相關研究文獻眾多，然而國防預算配置之文獻卻相當稀少。本研究提供一新的國防預算配置模型，以求取各項軍事投資標的之適當配置比例。首先，本研究蒐整1992至2004之預算資料並給予分類，以及透過對資深軍官之問卷，獲得防禦能力指標。本文定義之防禦能力指標係指「在美、日等國不介入的情況下，國軍能在一特定時間內成功保衛國家安全的可能性」。其次，本文引用倒傳遞類神經網路模擬防禦能力指標與各項軍事投資比例之適配函數；最後，運用基因遺傳演算法求取各項軍事標的之最適投資比例。研究結果顯示，在當前國防預算水準下，若能妥善規劃與運用預算，則能顯著增加國軍之防禦能力，而且武器系統更新與資訊戰兩投資項目應適度增加。

National defense budget is a measurement of a nation's potential to achieve its military strategic goals. Allocating and utilizing the limited budget to various military objectives carefully will promote the military force and therefore enhance the assurance of national security. Budget allocation has been a popular research topic, but the allocation issue of national defense budget has rarely been considered in such research. This study proposes an alternative procedure to find an appropriate budget allocation ratio with respect to each military investment objective. First, we surveyed and clustered the financial data structure of ROC from 1992 to 2004 carefully, and obtained the defense-competence against PRC by the means of questionnaire designed for superior officers. The ”defense-competence” considered here is ”the probability of assurance of national security more than a scheduled time horizon when ROC operations against PRC by military force owning itself. Second, a fitness function between defense-competence and budget allocation is simulated using back-propagation neural network. Finally, a genetic algorithm is utilized to find a near-optimal allocation portfolio for all military investment objectives. The results demonstrate that the defense-competence will increase significantly if current level of budget is allocated effectively, as well as the investments of renew of weapon systems and the information warfare should be higher than the current level.

1. Bosch-Domenech, A.,Escribano C.(1998).Regional Allocation of Public Funds: An Evaluation Index.Environment and Planning A,20,1323-1333.
2. Bosch-Domenech, A.,Escribano C.(1998).Regional Allocation of Public Funds: An Evaluation Index.Environment and Planning A,20,1323-1333.
3. Carter, A. E.,Ragsdale, C. T.(2002).Scheduling Pre-printed Newspaper Advertising Inserts Using Genetic Algorithms.International Journal of Management Science,30,415-421.
4. Carter, A. E.,Ragsdale, C. T.(2002).Scheduling Pre-printed Newspaper Advertising Inserts Using Genetic Algorithms.International Journal of Management Science,30,415-421.
5. Chiang, C. L.,Su, C. T.,Wang, F. S.(2002).Augmented Lagrangian Method for Evolutionary Optimization of Mixed-Integer Nonlinear Constrained Problems.International Mathematical Journal,2(2),119-154.
6. Chiang, C. L.,Su, C. T.,Wang, F. S.(2002).Augmented Lagrangian Method for Evolutionary Optimization of Mixed-Integer Nonlinear Constrained Problems.International Mathematical Journal,2(2),119-154.
7. Corbett, C. J.,Debets, F. J. C.,Van Wassenhove, L. N.(1995).Decentralization of Responsibility for Site Decontamination Projects: A Budget Allocation Approach.European Journal of Operational Research,86,103-119.
8. Docwra, G.,Strong S.(1985).Road Fund Allocation: An Analysis of Decision Criteria.International Journal of Transport Economics,12(3),283-300.
9. Docwra, G.,Strong S.(1985).Road Fund Allocation: An Analysis of Decision Criteria.International Journal of Transport Economics,12(3),283-300.
10. Goldberg, D. E.(1994).Genetic and Evolutionary Algorithm Come of Age.Communication of the ACM,37(3),113-119.
11. Holland, J. H.(1992).Adaptation in Natural and Artificial System: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence.MIT press.
12. Holland, J. H.(1992).Adaptation in Natural and Artificial System: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence.MIT press.
13. Lee, K. Y.,Yang, F. F.(1998).Optimal Reactive Power Planning Using Evolutionary Algorithms: A Comparative Study for Evolutionary Programming, Evolutionary Strategy, Genetic Algorithm, and Linear Programming.IEEE Trans. on Power Systems,13(1),101-108.
14. Lootsma, F. A.,Mensch T. C. A.,Vos, F. A.(1990).Multi-Criteria Analysis and Budget Reallocation in Long-term Research Planning.European Journal of Operational Research,47,293-305.
15. Lotfy, E. A. M.,Samech, A.(2002).Applying Neural Networks in Case-Based Reasoning Adaptation for Cost Assessment of Steel Buildings.International Journal of Computers & Applications,24(1),28-38.
16. Minami, K.,Nakajima, H.,Toyoshima, T.(1999).Real-time Discrimination of Ventricular Tachyarrhythmia with Fourier-Transform Neural Network.IEEE Trans. on Biomed. Engineering,46(2),179-185.
17. Mitsuo, G.,Cheng, R.(1997).Genetic Algorithms and Engineering Design.McGraw-Hill.
18. Mitsuo, G.,Cheng, R.(1997).Genetic Algorithms and Engineering Design.McGraw-Hill.
19. Moribayashi, M.,Wu, C. Y.(1990).A Decision Support System for Capital Budgeting and Allocation.Computers and Industrial Engineering,19(1),524-528.
20. Reategui, E. B.,Campbell, J. A.,Leao, B. F.(1997).Combining a Neural Network with Case-Based Reasoning in a Diagnostic System.Artificial Intelligence in Medicine,9(1),5-27.
21. Zanakis, S. H.(1991).A Multicriteria Approach for Library Needs Assessment and Budget Allocation.Socio-Economic Planning Sciences,25(3),233-245.
22. 林小萍(1999)。華梵大學工業管理研究所。
23. 林小萍(1999)。碩士論文(碩士論文)。華梵大學工業管理研究所。
24. 國防部(2000)。中華民國八十九年國防報告書。
25. 國防部(2000)。中華民國八十九年國防報告書。
26. 國防部(2000)。國軍軍事戰略要綱。
27. 國防部(2000)。國軍軍事戰略要綱。
28. 張寶光(1998)。碩士論文(碩士論文)。國防管理學院資源管理研究所。
29. 張寶光(1998)。國防管理學院資源管理研究所。
30. 陳勁甫、張正昌、孟德中(2004)。專案推移理論內涵暨其於軍事戰略規劃應用研究－以建構地面防衛作戰能量爲例。2004年ING安泰管理碩士論文獎暨研討會，台北:
31. 陳勁甫、張正昌、孟德中(2004)。專案推移理論內涵暨其於軍事戰略規劃應用研究－以建構地面防衛作戰能量爲例。2004年ING安泰管理碩士論文獎暨研討會，台北:
32. 黃道淵(1999)。碩士論文(碩士論文)。國防管理學院資源管理研究所。
33. 黃道淵(1999)。國防管理學院資源管理研究所。