期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：2
页码：1690
DOI：10.15680/IJIRCCE.2017.0502084
出版社：S&S Publications
摘要：Knowledge mining provides the methodology and technology to alter the medical data mining ofknowledge into helpful information for decision creating. By victimization data processing techniques it takes less timefor the prediction of the illness with additional accuracy. Among the increasing analysis on kidney illness predictingsystem, it has happened to vital classify the analysis of the outcomes and offers users with an definition of the existingrenal illness prediction techniques in every class. Knowledge mining tools and algorithms will provide results to tradequeries that conventionally used multiple times which is dominant factor to decision making. In this proposed researchwe tend to research completely different methods and additional algorithms of knowledge mining used for theprediction of risk issue on urinary organ illness.This paper provides a quick and straightforward result of completely different prediction models in knowledgemining and helps to seek out greatest model for any work. This prediction accuracy will be increased by increasing therange of attributes for the existing system of our previous work. The symbolic Fuzzy C Means algorithm will be testedwith the unstructured knowledge offered in health care business knowledgebase by modifying into fuzzified structuredknowledge with enhanced attributes and with a group of additional range of records to give higher accuracy to thesystem in predicting and diagnosing the patients of renal disorder. The Proposed system helps in predicting the earlierrisk factors of the kidney failure instead of clustering the severity of the disease based on the medical tests conductedby physicians. This thesis work is implemented by MATLAB.
关键词：DM techniques; Clustering techniques; k-means algorithm; fuzzy c means (FCM) algorithm; Kidney;diseases; Fuzzy Score
