Diabetes classification using ID3 and naïve Bayes algorithms
Other Title(s)
تصنيف مرض السكري باستخدام الخوارزمية التكرارية و خوارزمية المصنف الساذج
Joint Authors
Jasim, Khalid Shakir
Salih, Hadil Muhammad
Source
Journal of University of Anbar for Pure Science
Issue
Vol. 12, Issue 3 (31 Dec. 2018), pp.38-46, 9 p.
Publisher
University of Anbar College of Science
Publication Date
2018-12-31
Country of Publication
Iraq
No. of Pages
9
Main Subjects
Information Technology and Computer Science
Abstract EN
Diabetes can be defined as a chronic disease identified by high levels of blood glucose that result from issues in the way insulin is generated, the way insulin works, or both those reasons.
The aim of this research is to propose a technique using the Decision Tree (ID3) and Naive Bayes to categorize diabetes and reduce classification errors by increasing the accuracy of the classification.
The results of the proposed method were evaluated by comparing them with other results through the application of the proposed system to Pima India Diabetes data set, obtained from the UCI database site.
The experimental results show that the ID3 recorded a precision ratio of 91% and the naive class corrected it to 94% for the same number of the test group.
American Psychological Association (APA)
Jasim, Khalid Shakir& Salih, Hadil Muhammad. 2018. Diabetes classification using ID3 and naïve Bayes algorithms. Journal of University of Anbar for Pure Science،Vol. 12, no. 3, pp.38-46.
https://search.emarefa.net/detail/BIM-919079
Modern Language Association (MLA)
Jasim, Khalid Shakir& Salih, Hadil Muhammad. Diabetes classification using ID3 and naïve Bayes algorithms. Journal of University of Anbar for Pure Science Vol. 12, no. 3 (2018), pp.38-46.
https://search.emarefa.net/detail/BIM-919079
American Medical Association (AMA)
Jasim, Khalid Shakir& Salih, Hadil Muhammad. Diabetes classification using ID3 and naïve Bayes algorithms. Journal of University of Anbar for Pure Science. 2018. Vol. 12, no. 3, pp.38-46.
https://search.emarefa.net/detail/BIM-919079
Data Type
Journal Articles
Language
English
Notes
Record ID
BIM-919079