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
Versa Christian Wijaya
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 
Deteksi Tingkat Kemanisan Buah Melon melalui Ekstraksi Fitur Local Binary Pattern dengan Klasifikasi K-NN berbasis Raspberry Pi 4 Versa Christian Wijaya; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 1 (2022): Januari 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Indonesia is a country with a subtropical climate and is good at growing fruits and vegetables and other crops. Various variants are easily available, one of which is Sky Rocket Melon. This melon is round and green or yellow in color. Melon fruit tastes sweet and juicy flesh. To assess the sweetness of the melon, it is necessary to separate the flesh and taste of the melon. When buying melons, buyers cannot choose melons correctly because they cannot immediately know the level of sweetness. From these problems, a study was formed to determine the level of sweetness of melons accurately by reading the texture of the skin. The advantage of this research is that you don't need to split and taste the melon first to know the sweetness, but only use the image of the melon skin texture. This study uses the Local Binary Pattern method to perform feature extraction calculations, P=8,16,32 is the number of neighbors to be compared, and R=1,2,4 is the center radius or pixel value of adjacent distances. The results of feature extraction are inputted into the K-Nearest Neighbor or K-NN algorithm, and classified into one of three categories (low, average, high) with values ​​of K=3, K=5, and K= 7. Testing uses up to 360 images of training data, up to 90 images of test data, and the test kit uses 15 melons as images. The results of the P and R tests of the Local Binary Pattern algorithm and the K value on K-NN provide the highest level of accuracy of 91.11%. By using the value of P = 8, the value of R = 1, and the value of K = 3. Testing the hardware system using Raspberry Pi 4, with the result that the accuracy rate is 80% and the average calculation time is 0.22084 seconds.
Co-Authors Utaminingrum, Fitri