Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Renita Leluxy Sofiana
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 
Implementasi Sistem Pendeteksi Atrial Fibrillation Berbasis Arduino Uno Menggunakan Metode Support Vector Machine Renita Leluxy Sofiana; Rizal Maulana; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 1 (2021): Januari 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Many cases of coronary heart disease that cause sudden death because the patient has a history of arrhythmias. In addition, 1 in 6 stroke patients are also caused by arrhythmias. According to cases that often occur in hospitals, Atrial Fibrillation arrhythmias are one of the factors that cause stroke because patients with Atrial Fibrillation arrhythmias have a five times greater risk of stroke because it can cause blockage of blood vessels. Prevention for this disease can be done by conducting early examinations so treatment can be done quickly. Currently, atrial fibrillation arrhythmia examination can only be done in a hospital, which is quite expensive and this examination cannot be done independently. This study uses the AD8232 sensor to generate ECG signals, the Arduino Uno as a data processor, and the LCD to display the results of the diagnosis, "Normal" or "Atrial Fibrillation". The system will use the BPM feature, mean RR interval, and median RR interval to perform Support Vector Machine classification. Starting with 24 training data to produce a hyperplane. Furthermore, data testing is carried out to classify. The results obtained from the BPM accuracy test were 12 times the result of 95.42%. The classification using Support Vector Machine method resulted an accuracy, training time, and testing consecutively 83.33%, 219.30 ms, and 0.09 ms using 12 test data.
Co-Authors Rizal Maulana Utaminingrum, Fitri