Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Linda Silvya Putri
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 Minyak Goreng Berdasarkan Frekuensi Penggorengan Menggunakan Metode K-Nearest Neighbor Berbasis Raspberry Pi Linda Silvya Putri; Fitri Utaminingrum; 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 (1195.974 KB)

Abstract

Cooking oil is often used by the people as stapel for frying food ingredients. There are several types of oil, one of which is vegetable oil. Vegetable oil contains essential fatty acid which has function to prevent constriction of blood vessel that will effect accumulation of cholesterol. The cooking oil used repetitively can cause various diseases. The cooking oil used repetitively will make the double bonds of oxidized oil, and form peroxide groups and cyclic monomers, and will contain trans fatty acid. From these problems, it is necessary to have a system that can classify frequency of the use of cooking oil. In this study, the parameters studied in cooking oil are from color and turbidity. To determine classification of the frying frequency in cooking oil, for color detection of R (Red), G (Green), B (Blue) is obtained from the results of raspberry pi camera readings, and for turbidity is obtained from LDR (Light Emitting Diode) readings by Raspberry Pi 3 by using the KNN (K-Nearest Neighbor) method. From the results of study, it is known that the percentage of accuracy from R (Red), G (Green), B (Blue) readings on a raspberry pi camera with TCS3200 censor is R = 98.102%, G = 98.072%, B = 96.732%. In study of system using the KNN (K-Nearest Neighbor) method with 72 training data and 30 test data, is obtained an accuracy K=1, K=3, K=5 73.33% with an average time computing system of 3.9 ms.
Co-Authors Tibyani Tibyani Utaminingrum, Fitri