Open AccessIdentifikasi Penyakit Diabetes Mellitus Melalui Nafas Berbasis Sensor Gas Dengan Metode Fast Fourier Transform dan Backpropagation
Author(s) -
Mohammad Hafiz Hersyah,
Andrizal Andrizal,
Revinessia Revinessia
Publication year - 2018
Publication title -
jitce (journal of information technology and computer engineering)
Language(s) - English
Resource type - Journals
ISSN - 2599-1663
DOI - 10.25077/jitce.2.02.85-91.2018
Subject(s) - diabetes mellitus , backpropagation , saliva , medicine , hydrogen sulfide , artificial neural network , artificial intelligence , computer science , materials science , endocrinology , sulfur , metallurgy
The purpose of this research is to detect whether a person has diabetes mellitus or not. In people with diabetes mellitus uncontrolled will result in a decline in the rate of saliva that results in bad breath. The system uses the sensor TGS 2602 and MQ 4. It's function is to detect the levels of Hydrogen Sulfide and Methan in a person’s breath. The decision is made by using the neural network with a backpropagation method. The result for 5 (five) tests of diabetes mellitus samples can be detected with a success rate of 80%, whereas using random samples, the test detected with detected with a success rate of 80% samples that didn’t contain diabetes mellitus. This system could provide a solution for testing if a person is suffering from diabetes mellitus