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：2018
卷号：6
期号：3
页码：2350
DOI：10.15680/IJIRCCE.2017.0603105
出版社：S&S Publications
摘要：Diabetes occurrence is a standout amongst the most genuine wellbeing challenges in both maidenlydeveloped and developing nations. Nonetheless, it is for certain that the early recognition and exact conclusion of thisillness can diminish the danger of alliance to other significant ailment in diabetes patients. On account of the viablearrangement and high symptomatic ability, master frameworks and machine learning methods are presently picking upprominence in this field. In this investigation and review least square support vector machine (LS-SVM) along withadditive regression and decision tree will be used for diabetes identification and forecasting. The efficacy of the LSSVMis examined on Pima Indian diabetes dataset using k-fold cross validation scheme along-with AdditiveRegression and Decision Tree. Compared to thirteen well-known methods for the diabetes diagnosis in the literature,the study results showed the effectiveness of the proposed method. The forecasting unit analyzes the attributespertaining blood sugar measures with others variants over serene and endow with appropriate attentivenesscommunication and results to the patient through prevailing conditions information and scenarios.
关键词：Diabetes mellitus; Additive Regression; Decision Tree; Least Square Support Vector Machine.
