Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JURIKOM (Jurnal Riset Komputer)
Dikan Ismafillah
Universitas Buana Perjuangan, Karawang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 1 Documents
Search
Journal : JURIKOM (Jurnal Riset Komputer)

 1 
Implementasi Model Support Vector Machine dan Logistic Regression Untuk Memprediksi Penyakit Stroke Dikan Ismafillah; Tatang Rohana; Yana Cahyana
JURIKOM (Jurnal Riset Komputer) Vol 10, No 1 (2023): Februari 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v10i1.5478

Abstract

In this study the topic raised was about stroke. Based on the statistical results of the Indonesian Health Service Research Agency (2018), stroke is the disease in the first order in Indonesia. Previous studies have carried out stroke research including research that took data from patients at Abdul Wahab Sjahranie Hospital. The model used is the Machine Learning Decision Tree, with an accuracy of 87.5%. For better accuracy, this study predicts stroke using two algorithms, namely support vector machine (SVM) and logistic regression (LR). In the stroke data found there were 10 attributes and 1 output, which consisted of gender, age, hypertension, heart_disease, ever_married, work_type, Residence_type, avg_glucose_level, bmi, smoking_status, and stroke(output). This study uses the SVM+SMOTE model with a confusion matrix and K-Fold and uses 4981 rows and 11 columns. Based on the research results, the support vector machine algorithm is better than the logistic regression (LR) algorithm in predicting datasets using the oversampling and cross-validation methods. Testing the SVM + SMOTE model using the confusion matrix and the K-Fold method produces much better accuracy in the distribution of stroke data accurately. The results show that the Support Vector Machine classification algorithm can work effectively with perfect accuracy of 95.3% at the 10K-Fold Validation level.
Co-Authors Tatang Rohana Yana Cahyana