Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Althaf Banafsaj Yudhistira
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 Deteksi Dini dan Klasifikasi Jenis Urine dengan Metode K-Nearest Neighbor (KNN) pada Pasien Operasi Althaf Banafsaj Yudhistira; Rizal Maulana; Dahnial Syauqy
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 9 (2021): September 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Urine produced by each person may vary based on its physiological. It was happened by some reason like daily diet, gender, condition of exrectory system, and so on. These factor may lead physiological change of urine like color and turibidity. That is why urin often used to determine a person's health condition. In other side doing traditional urine analysis error often occurs because it only rely on analyzer sight. Analysis of a person's condition through urine physical conditions is also very much needed in the operation process and it is not possible if periodic analysis is carried out continuously during the operation. Therefore we need a tool that can perform automatic analysis to minimize errors in analysis and taking patient handling actions. This study uses the TCS3200 sensor to extract features in the form of color and an IR Proximity sensor for urine fluid turbidity. The two features will be processed by Arduino Uno to carry out the classification process. The urine will be divided into three classes, namely: Normal Urine, Blood Urine, Pus Urine. The classification process will use the K-Nearest Neighbor method with varying K values ​​starting from K = 3, K = 5, and K = 7. The system was able to recognize urine with an accuracy of 86.7% then 86.7% and 80% respectively
Co-Authors Dahnial Syauqy Rizal Maulana