應用類神經網路於投保單位投保金額申報稽核之研究

The Study of Using Artificial Neural Network to Inspect The Insurance of Insured Unit

鄭文進(Wen-chin Cheng)

指導教授 ： 黃有評 ； 謝尚琳

大同大學/電機資訊學院/資訊工程學系所/碩士(2009年)

摘要

全民健康保險係一種自助互助危險分擔之社會保險制度，為達此目的，必須全體國民均依規定參加保險，繳交保險費，以享受適當的醫療照顧。因此，如何落實全民強制納保辦理投保手續，及防範杜絕違法之情事發生，以期建立永續經營的全民健康保險制度是健保局所努力的目標。本研究主要是運用倒傳遞網路與基因演算法技術，從投保金額申報異常資料中，建構出可用以預測投保金額申報異常之分類模型，有效協助稽核人員掌握投保金額申報異常之投保單位，減少因稽核人員誤判造成投保單位必須執行申覆之煩瑣作業程序。實驗結果顯示，利用所提方法可提昇正確辨識率達到94.24%，比一般稽核人員判別的正確率84.63%高出許多。

關鍵字

人工智慧 ； 倒傳遞網路 ； 基因演算法 ； 投保金額

並列摘要

National Health Insurance that social insurance system that shared dangerously that one kind helps each other by oneself. For reach purpose this, must all people in accordance with participate in insurance to stipulate, pay insurance premium, in order to enjoy proper medical care. So how implement the whole people to receive and go through formalities of insuring by force, and take precautions against and stop the illegal thing happening, and expect the whole people health insurance managed continuously forever to set up system to National Health Insurance diligent goal.
This research is mainly to use back-propagation neural network and genetic algorithm technology. From the insurance in the unusual materials, build and predict that declares the unusually categorized model in the insurance. Help to audit personnel and grasp the insurance to declare unusual of insured unit. Must carry out and explain the convoluted operation procedure covered to insure the unit to cause by the fact that audit personnel to judge by accident while reducing. The experimental result shows, utilize the methods proposed to promote the correct distinguish rate up to 94.24% higher than generally audits the correct rate that personnel differentiate 84.63% .

並列關鍵字

Artificial intelligence ； back-propagation neural network ； genetic algorithm ； insurance

參考文獻

[4] 謝景堂，類神經網路於隔震結構動力分析之應用，中原大學土木工程研究所碩士論文，2004年。

[21] B.K. Wong, T.A. Bodnovich and Y. Selvi, “Neural network applications in business: a review and analysis of the literature (1988-95),” Decision Support Systems, vol. 19, pp.301-320, Feb. 1997.

[22] S.T. Kazadi, “Conjugate schema and basis representation of crossover and mutation operators,” Evolution Computation, vol. 6, pp.129-160, 1998.

[23] C.F. Tsai, C.W. Tsai, C.P. Chen and F.C. Lin, “A modified multiple-searching approach to genetic algorithms for solving traveling salesman Problem,” in Proc. of Joint Conf. on Information Sciences, Pingtung, Taiwan, vol. 3, pp.362-366, Oct. 2002.

[24] M. Bessaou and P. Siarry, “A genetic algorithm with real-value coding to optimize multimodal continuous functions,” Structural and Multi-disciplinary Optimization, vol. 23, pp.63-74, Dec. 2002.