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
Yohana Angelina Sitorus
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 
Prototype Palang Pintu Kafe Otomatis pada Sistem Pendeteksi Gejala Covid-19 menggunakan Metode Support Vector Machine Yohana Angelina Sitorus; Rizal Maulana; Agung Setia Budi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 10 (2022): Oktober 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

One of the efforts made to suppress the spread of the corona virus in crowded places such as cafes is by checking body temperature and limiting the number of visitors according to PPKM regulations in the Java-Bali area. However, the body temperature parameter is not accurate enough to detect suspected Covid-19 symptoms and the calculation of visitor capacity is still not effective, which is still done manually. In addition, control over the cafe entrance is also needed considering the number of visitors coming or going. This study aims to develop a Covid-19 symptom measurement system using three parameters, namely body temperature, blood oxygen saturation and respiratory frequency using the Support Vector Machine (SVM) method to classify visitors into healthy and symptomatic classes. The system also provides output in the form of sound, information on the number of visitor capacities, and the application of miniature doorstops using a servo motor that moves according to the classification results. Tests of each sensor resulted in a very good average accuracy. The measurement of body temperature with the MLX90614 sensor is 99.26%, the measurement of oxygen saturation with the MAX30100 sensor is 98.95, the breath frequency measurement with the sound sensor reaches 100%, and the visitor capacity counter with the PIR sensor is 100%. Classification using the SVM method produces an average accuracy of 100% with an average computation time of 131.6 s. In addition, the output in the form of sound and movement from the miniature doorstop can work as expected.
Co-Authors Agung Setia Budi Rizal Maulana