Johannes Archika Waysaka
Fakultas Ilmu Komputer, Universitas Brawijaya

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Pengembangan Sistem Pemilah Telur Ayam Negeri dan Ayam Kampung berdasarkan Berat dan Warna Cangkang Telur menggunakan metode K-Nearest Neighbor (K-NN) Johannes Archika Waysaka; Dahnial Syauqy; Mochammad Hannats Hanafi Ichsan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 10 (2021): Oktober 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Eggs are one of the nutritious foods that contain animal protein that is good for the body. Eggs themselves are popular in Indonesia, which can be seen from the demand for eggs that increases every year. From BPS information from 2015 around 13 tons, 2016 rise to 303 tons, and in 2017 it increased by around 386 tons it can be concluded that from 2015 to 2017 it increased by 2824%. In Indonesia, there are 2 types of chicken eggs, namely native chicken eggs and domestic chicken eggs. The difference between these two eggs is in their weight and color. Native chicken eggs have a lighter weight than domestic chicken eggs and the color of native chicken eggs is brighter than domestic chicken eggs. From the difference in parameters, some ordinary people have difficulty distinguishing them. Based on these problems, it is necessary to create a system capable of sorting chicken eggs automatically. The system is made using a loadcell sensor to measure the weight of the egg, and use the TSC3200 sensor to get the value of eggs based on red, green, and blue. The data taken from the two sensors is then processed using the K-Nearest Neighbor method with the output in the form of a servo that moves towards the egg, all systems are processed using Arduino mega. Testing is focused on the functionality, accuracy, and performance of the system. From the functional testing that has been done the system gets 100% correct results. So it can be said that this system is successful. For the K test, the system was tested using a K value of 3,5,7 with 20 training data and 20 test data, which obtained accuracy of 100%, 99%, and 98.57% respectively. And the system performance test obtained a processing time speed of 568.8 ms when using K3.