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
Nur Aini Afifah Isbindra
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 Nabati Menggunakan Sensor Warna dan Sensor Cahaya dengan Metode K Nearest Neighbor (KNN) berbasis Arduino Nur Aini Afifah Isbindra; Hurriyatul Fitriyah; Dahnial Syauqy
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 4 (2022): April 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Vegetable oil is one of a product from plants and is often used as the main ingredient in food processing. Each plant that is used as a source of this oil produces different vegetable oils in terms of nutritional content. Oils that have high health benefits for the body are usually sold at high prices in the market. The similarity of the characteristics of the oil in terms of its physical make some producers deliberately sell vegetable oil that is not in accordance with the original plant source. To minimize this incident, in this study a system was created to distinguish vegetable oils based on plants directly and quickly. RGB parameters as well as turbidity are used as features in the classification. RGB data is acquired by the TCS34725 color sensor, while the turbidity data will be obtained by the LDR light sensor. The classification method itself uses the K-NN (K-Nearest Neighbor) algorithm. The K-NN method uses training data as a classification system training to calculate the distance from the test data which is the new data that is entered into the system. Then the results of the distance calculation will be sorted from the closest and the results will be determined based on the most selected class in the voting as many as K. Based on the accuracy test of the classification method, an accuracy of 87.5% was obtained from K=3 and K=5. Then the average computational speed of the classification is 103.6 ms.
Co-Authors Dahnial Syauqy Fitriyah, Hurriyatul