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

• Main Authors: Wen-chin Cheng, 鄭文進
• Other Authors: Yo-ping Huang
• Format: Others
• Language: zh-TW
• Published: 2009
• Online Access: http://ndltd.ncl.edu.tw/handle/54937488378557417094

碩士 === 大同大學 === 資訊工程學系(所) === 97 === 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% .