Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Annisa Puspitawuri
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Diagnosis Tingkat Risiko Penyakit Stroke Menggunakan Metode K-Nearest Neighbor dan Naive Bayes Annisa Puspitawuri; Edy Santoso; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (314.342 KB)

Abstract

Stroke is a disease that arises due to the dissolution of blood supply to the brain because of bursts in the blood vessels or there was a blockage of blood clots. The supply of oxygen and nutrients to the brain stops and can cause damage to the tissues in the brain. Stroke is number one leading cause of disability and number three cause of death after cancer and heart disease. Based on Riskesdas data, stroke prevalence in Indonesia in 2013 has increased when compared with Riskesdas data in 2007 with a value of 8.3%, increase up to 12.1% per 1,000 population. Therefore, we need an action to detect the level of risk of stroke to be immediately addressed in accordance with the level of risk. This research proposes an application of diagnosis of stroke risk level using K-Nearest Neighbor and Naive Bayes methods, because the data obtained using numerical and categorical attributes. K-Nearest Neighbor algorithm is used to process numerical data, and Naive Bayes algorithm is used to process categorical data. The results showed that the highest accuracy value obtained in the balanced class data was 96.67% with 45 training datasets, 30 testing datasets and value of K=15-22. Meanwhile, the training datasets that is not balanced shows the highest accuracy of 100% with the number of training datasets is 60, 30 testing datasets and the value of K=20-30.
Co-Authors Candra Dewi Edy Santoso