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
Muhammad Yusuf Ramadan
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 Metode Klasifikasi Support Vector Machine (SVM) Terhadap Pemakaian Minyak Goreng Muhammad Yusuf Ramadan; Dahnial Syauqy; Tibyani Tibyani
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 (626.824 KB)

Abstract

The use of cooking oil repeatedly and beyond the normal limits (waste cooking oil) can cause variety of dangerous diseases to human health such as heart failure, stroke, coronary heart disease, and others. However, currently the use of recurrent cooking oil is still high. This is shown from the results of research in Semarang City, showing that 75% of respondents people use the same cooking oil for frying as much as 61.2 percent use it twice, 19.6 percent use it three times, and 5.4 percent use it as four time. Based on problems, it is necessary to have an automation system for classifying the frequency of the using cooking oil, so it can be used for the frequency classification of the use of cooking oil that has been used several times (waste cooking oil) accurately. In this study, the parameters used were the color and turbidity level of cooking oil. Determination of cooking oil classification is based on color and turbidity level of cooking oil was obtained from TCS3200 color sensor readings ADC and the resistance of the photodiode sensor by the Arduino uno microcontroller using the Support Vector Machine methods, because this method is one of the classification methods that are still rarely used, easy to understand, more accurate and has high computational speed. From the results of the tests performed, it is known the percentage error reading TCS3200 color sensor is 3.31% and the photodiode sensor can work well. So, if the cooking oil is more turbid, the value of the photodiode sensor is bigger. Furthermore, in testing the system using the Support Vector Machine method with the amount of training data as many as 60 data and test data as many as 13 data, obtained an accuracy of 92.3% with the average computing time for 4384.53 ms.
Co-Authors Dahnial Syauqy Tibyani Tibyani