Genetic Algorithm-based K-means Clustering Technique And Its Application To Cardiac Disease Diagnosis

碩士 === 義守大學 === 資訊管理學系 === 100 === With the rapid advancement of science and technology, diseases resulting from the development of civilization have increased in our daily life. Heart diseases are among them and have become more and more widespread in recent years due to the change in people's...

Full description

Bibliographic Details
Main Authors: Kan, Fengjung, 甘豐榮
Other Authors: Liu, Jennlong
Format: Others
Language:zh-TW
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/39793384358869647744
Description
Summary:碩士 === 義守大學 === 資訊管理學系 === 100 === With the rapid advancement of science and technology, diseases resulting from the development of civilization have increased in our daily life. Heart diseases are among them and have become more and more widespread in recent years due to the change in people's diet and lifetime habits such as smoking, drug abuse, and the increase in the consumption of animal products, fat, and sugar. In addition, great pressure coming with the urbanization may cause people to easily have high blood pressure. The obvious lack of exercise increases the chance of obesity. All of the factors mentioned above put people in high risk of heart disease. In medicine science, there is no clear definition for the causes of heart diseases. Therefore, this study adopts the concept of Evolution of Data Mining, which combines Genetic Algorithms with k-means Clustering Algorithms, to effectively raise the accuracy in the sole use of k-means. In addition, it also uses Weka software to perform simple data mining cases for providing accuracy comparison with clustering algorithm based on Cost Matrix to try to research into some possible causes of heart diseases and find out knowledge rules from the data of patients in order to put them into practical use.