Claim Missing Document
Check
Articles

Found 1 Documents
Search

Penerapan Metode Neighbor Weighted K-Nearest Neighbor Dalam Klasifikasi Diabetes Mellitus Dendry Zeta Maliha; Edy Santoso; Muhammad Tanzil Furqon
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (334.316 KB)

Abstract

Diabetes mellitus is a critical illness caused by abnormal irregular insulin secretion in an increase in blood sugar. Diabetes mellitus can increase glucose in the body, resulting in complications that can lead to several risks, namely heart disease, stroke, kidney failure, death and blindness According to the World Health Organization (WHO), as many as 300 million people in the world will be affected by diabetes by 2025 In addition there are some diseases that have early symptoms that are almost similar to diabetes mellitus, if you make a mistake to analyze it will be fatal in people with diabetes mellitus. Therefore an application is needed that can facilitate the classification of diabetes mellitus. In this study propose the application of the Neighbor Weighted K-nearest Neighbor method in the classification of diabetes mellitus. The NWKNN method uses weighting in the data class. The results showed the average accuracy using the value of K = 15 and the value of E = 2 obtained an accuracy of 92.3% in the training data of 130 data divided into 10 fold and test data as many as 13 data in each fold.