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
Shafa Sabilla Zuain
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 Penyakit pada Daun Cabai berdasarkan Fitur HSV dan GLCM menggunakan Algoritma C4.5 berbasis Raspberry Pi Shafa Sabilla Zuain; Hurriyatul Fitriyah; Rizal Maulana
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 9 (2021): September 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Chili plants are plants with great economic potential in Indonesia. Nevertheless, every year chili production has decreased, one of which is due to disease. Observation of conditions in chili plants can be seen in the changes that occur in chili leaves. Disease detection in chili leaves is needed to minimize the risk of crop failure in chili plants and as a strategic control effort. The number of types of diseases in chili plants is quite a lot and knowledge about the symptoms of the disease is not enough to make it quite difficult for farmers to determine the type of disease that attacks. Therefore, a system that is able to detect diseases in chili leaves is needed. Disease Detection System on Chili Leaves Based on HSV and GLCM Features Using the C4.5 Algorithm Based on Raspberry Pi is used to detect types of diseases on chili leaves. This research uses Hue, Saturation and Value (HSV) color features and Gray Level Co-occurence Matrices (GLCM) texture features. The HSV color feature was used to analyze diseased leaf discoloration. Texture features are used to analyze changes in the texture of chili leaves with the help of five features from GLCM, namely correlation, dissimilarity, homogeneity, contrast, and energy with four variations of angles, namely angles 0, 45, 90 and 135. The classification method used is using a decision tree from C4.5 algorithm with classification results in the form of sercospore spot disease, curly mosaic and normal conditions. Detection of disease in chili leaves using this method using 21 test data to get an accuracy of 86%. The average execution time required by the system to detect is 1.045 seconds.
Co-Authors Fitriyah, Hurriyatul Rizal Maulana