Article Per Year (5 Year)
p-Index From 2019 - 2024
0.408
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Paul L Tahalele
Universitas Katolik Widya Mandala
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Perbandingan Performansi Algoritma Pengklasifikasian Terpandu Untuk Kasus Penyakit Kardiovaskular Adi Nugroho; Agustinus Bimo Gumelar; Adri Gabriel Sooai; Dyana Sarvasti; Paul L Tahalele
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 5 (2020): Oktober 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (477.038 KB) | DOI: 10.29207/resti.v4i5.2316

Abstract

One of the health problems that occur in Indonesia is the increasing number of NCD (Non-Communicable Disease) such as heart attack and cardiovascular disease. There are two factors that cause cardiovascular disease, i.e. factor that can be changed and cannot be changed. This study aim to analyze the best performance of several classification algorithms such as k-nearest neighbors algorithm (k-NN), stochastic gradient descent (SGD), random forest (RF), neural network (NN) and logistic regression (LR) in classifying cardiovascular based on factors that caused those diseases. There are two aspects that need to be examined, the performance of each algorithm which is evaluated using the Confusion matrix method with the parameters of accuracy, precision, recall and AUC (Area Under the Curve). The dataset uses 425.195 samples from result data of cardiovascular disease diagnosed. The testing mode uses percentage split and cross-validation technique. The experimental results show that the performance of NN algorithms produces the best prediction accuracy compared to other algorithms, which is accuracy of 89.60%, AUC of 0.873, precision of 0.877, and recall of 0.896 using percentage split and cross-validation testing mode using Orange. For the accuracy of 89.46%, AUC of 0.865, precision of 0.875, and recall of 0.895 using cross-validation testing mode using Weka. By KNIME, the result of accuracy value is 88.55%, AUC value is 0.768, precision value is 0.854, and recall value is 0.886 using cross-validation testing mode.
Co-Authors Adi Nugroho Adri Gabriel Sooai Agustinus Bimo Gumelar Dyana Sarvasti