Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Lamidi Lamidi
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 dan Tingkat Dehidrasi Berdasarkan Kondisi Urin Dengan Metode Jaringan Saraf Tiruan Berbasis Aplikasi Android Lamidi Lamidi; Rizal Maulana; Wijaya Kurniawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1393.763 KB)

Abstract

Diabetes mellitus and dehydration in case serious level illness can cause death. However now a days the detection of diabetes mellitus in general uses examination of blood samples, and for dehydration is only based on the analysis of the health team by some clinical signs that cause dehydration. From these problems, there is a need a research about to automation systems to detect diabetes mellitus and levels of dehydration to reduce the number of people with diabetes mellitus and dehydration that untreated. On this research, the parameters used to compare diabetes mellitus and levels of dehydration are color, ammonia levels and pH of human urine. The reason of using urine as research object is because the condition of urine can reflect health conditions in the human body. Process to determine diabetes mellitus and levels of dehydration from color, ammonia levels and pH in human urine is perform with read data color sensor TCS3200, MQ135 gas sensor, and Liquid pH sensor by the Arduino Uno microcontroller with the Artificial Neural Network method. Applying Artificial Neural Network Architecture which has an input layer of 5 units of neurons, 6 units of neurons in 1 hidden layer, and an output layer with 2 neurons. Data training is carried out on other devices just not looking for weight values, for the main system only predictions are made from sensor readings. The system has accuracy of 80% with an average computing time of 2.03 seconds.
Co-Authors Rizal Maulana Wijaya Kurniawan