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
Hilman Syihan Ghifari
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 
Klasifikasi Kualitas Minyak Goreng berdasarkan Fitur Warna dan Kejernihan dengan Metode K-Nearest Neighbour berbasis Arduino Uno Hilman Syihan Ghifari; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 7 (2022): Juli 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Cooking oil is a staple ingredient that people consume in their daily life. There are various types of oil circulating among the public, including packaged oil, bulk oil, and used cooking oil. The use of cooking oil repeatedly can damage the quality of cooking oil and increase the risk of several diseases, including carcinoma. To determine the quality of oil, there are several kinds of chemical tests, including the determination of the peroxide number, saponification number, iodine number, and acid number. And can also be seen directly through the color and clarity of the oil. The design of this classification system uses color and clarity as input features of the system and used cooking oil as test objects and system datasets. To measure color and clarity, TCS3200 and LDR sensors are used. The classification process starts from inserting the used cooking oil object into a 50ml beaker glass, then inserting the beaker glass into the system with a 1cm position next to the TCS3200 and LDR sensors. The light will pass through the object and go to the TCS3200 and LDR sensors, then the reading results will be sent and processed via Arduino UNO using the K-Nearest Neighbor method and the final result in the form of proper and less appropriate classification will be displayed on the LCD monitor. The K-Nearest Neighbor classification was chosen because it is considered to have good accuracy with a limited dataset. The dataset is divided into 2, namely, 17 training data and 8 test data. From the results of the tests carried out with 8 test data for used cooking oil, the accuracy results were 75%.
Co-Authors Utaminingrum, Fitri