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
Farah Amira Mumtaz
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 
Sistem Pendeteksi Penyakit Diabetes Melitus berdasarkan Kondisi Urin dan Gas Buang Pernapasan menggunakan K-Nearest Neighbor berbasis Arduino Farah Amira Mumtaz; Rizal Maulana; Agung Setia Budi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 8 (2020): Agustus 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

One of the most dangerous chronic diseases in Indonesia is diabetes mellitus. This disease has symptoms characterized by high levels of glucose in human blood. Examination of diabetes mellitus that currently available is still invasive by taking blood samples using a needle into the patient's finger. The long period of time and the high cost are the constraint in getting the results of the examination. Research to detect diabetes mellitus in a non-invasive manner, which requires a small amount of money, and saves more time, is needed to overcome the existing problems. This research uses features in the form of urine and respiratory gas. In the patient's urine, the color and the level of ammonia gas will be detected. Meanwhile, in the patient's respiratory gas levels, methane gas will be detected. Data processing in the system using the Arduino Mega microcontroller. The processed data obtained from the output of the color sensor and gas sensor. The sensors are TCS3200 as a color sensor and the MQ-135 and MQ-4 sensors as gas sensors. The results of data processing will be classified using the K-Nearest Neighbor or K-NN method into Normal and Diabetes conditions. Testing using 12 test data and 24 training data with a value of K = 3 resulted in an accuracy of 91.67% because there was 1 data mismatch at the time of testing. The average system performance obtained based on 10 tests is 3061.9 ms.
Co-Authors Agung Setia Budi Rizal Maulana