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
Dwi Fitriani
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 Klasifikasi Diabetes Melitus Berdasarkan Kondisi Urin, Gas Buang Pernapasan, Dan Tekanan Darah Menggunakan Metode Naive Bayes Berbasis Arduino Dwi Fitriani; Rizal Maulana; Hurriyatul Fitriyah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 6 (2021): Juni 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Diabetes mellitus is a disease that attacks humans regardless of age. A person will have diabetes mellitus when blood sugar levels in the body increase, resulting in reduced insulin in the body. Diabetes examination can be done using a blood sugar test tool using a blood sample taken from a person's fingers. Examination in this way causes pain and discomfort. With this problem, this study aims to create a system that can be used to detect a person without using blood samples (non-invasive), saving time and costs in the examination. In the study of diabetes mellitus detection system using parameters of urine condition, respiratory exhaust gas and blood pressure. The conditions used are ammonia gas levels in human urine, respiratory exhaust gases used are acetone gas levels from human breath and human blood pressure. Data processing is carried out using arduino uno microcontroller. The data was obtained from the output sensors MQ-135, TGS-822 and MPX5700AP sensors. From the test results obtained the correlation value of sensors MQ-135 and TGS-822 with the output voltage of 99.29% and 98.56%, while for the sensor MPX5700AP known percentage of errors sistole and diastole by 8.90% and 4.64%. The system classifies diabetes mellitus using the Naive Bayes method. It uses 12 test data and 24 training data to determine the accuracy of Naive Bayes classification. Of the 12 test data there is 1 data whose class is not appropriate so that the accuracy value becomes 91.67%. Meanwhile, the average compute time of the system obtained in 10 tests is 1.02 seconds.
Co-Authors Fitriyah, Hurriyatul Rizal Maulana