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
Pandy Aldrige Simanungkalit
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 Telur Ayam Fertil dan Infertil Menggunakan Fitur Tekstur Dan Metode K-Nearest Neighbor Berbasis Raspberry Pandy Aldrige Simanungkalit; Hurriyatul Fitriyah; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 1 (2021): Januari 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Fertile chicken eggs are eggs that fertilized by a male and have potential to hatch while infertile eggs are eggs that not fertilized by a male. In chicken hatching management infertile eggs need to be removed from hatching machine so that they do not rot and explode in hatching machine. The removing process of infertile eggs from hatching machine doing by candling the eggs using a flashlight or lamp placed behind the eggs. In hatching industry with a large capacity doing this process is very tiring for the eyes because it requires high concentration and accuracy so this affects the consistency and accuracy of the observation results, therefor a system that classify fertile and infertile eggs constantly is needed. This study design classification system for fertile and infertile eggs based on Computer Vision with texture feature extracted using Gray Level Co-Occurrence Matrix method and classified using K-Nearest Neighbor method. To support the memory requirements for image processing the system is run on a raspberry pi device. The results of analysis and testing using K-Fold Cross Validation of Gray Level Co-Occurrence Matrix feature extraction show that the best feature combination is dissimilarity-correlation and Classification results using K-Nearest Neighbor show an accuracy rate of 93,33% on the number of neighbor K=7 and 9.
Co-Authors Eko Setiawan Fitriyah, Hurriyatul