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
Noza Trisnasari Alqoria
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 
Rancang Bangun Sistem Deteksi Kemanisan Buah Melon dengan Metode Gray Level Co-occurrence Matrix (GLCM) dan Support Vector Machine (SVM) Noza Trisnasari Alqoria; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 6 (2021): Juni 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Melon fruit has many benefits and vitamin content that is useful for health. There are various types of melons that are superior in Indonesia, one of which is the Sky Rocket Melon. This type of melon is round and has a thick, green rind. The entire surface of the skin is covered with gray nets and has greenish yellow flesh. Currently, there is no technology that can determine the sweetness level of a melon. To find out, it is necessary to split or slice some of the flesh. This method is considered very impractical, so it takes a technological innovation only with digital image analysis. This research uses the Gray Level Co-occurrence Matrix and Support Vector Machine methods. In this study, using variations in the value of d = 1, 2 and angular direction θ = 0 °, 45 °, 90 °, 135 ° with 5 features, namely contrast, homogeneity, energy, dissimilarity and correlation. The detection of melon fruit classes is divided into sweet and unsweetened classes using the Support Vector Machine (SVM) by testing 3 kernels, namely Linear, RBF and Polynomial. This study used a Raspberry Pi camera to take pictures of melons with a distance of 10 cm detected by the ultrasonic sensor. Melon detection results will be displayed on the 16x4 LCD. In ultrasonic sensor testing, an average error of 1.97% was obtained with an ultrasonic sensor accuracy of 98.03%. In testing this system, the highest accuracy was obtained by the RBF kernel with a variation of the distance d = 2 and the angular direction θ = 45 °, which was 86% with an average computation time of 8.5403 seconds.
Co-Authors Utaminingrum, Fitri