Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Nasional Teknik Elektro dan Teknologi Informasi
R. Rizal Isnanto
Departemen Teknik Komputer, Fakultas Teknik, Universitas Diponegoro
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

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

Found 1 Documents
Search

 1 
Klasifikasi Penyakit Daun Kopi Robusta Menggunakan Metode SVM dengan Ekstraksi Ciri GLCM Agus Supriyanto; R. Rizal Isnanto; Oky Dwi Nurhayati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 4: November 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i4.8044

Abstract

Many farmers in Indonesia derive their income from coffee plants, which also play a crucial role in the country’s foreign exchange earnings. However, coffee plant production may decrease due to pests and disease attacks. Leaf diseases, such as leaf spot (Cercospora coffeicola) and leaf rust (Hemileia vastatrix), are among the most common diseases to occur in coffee plants. This research seeks to identify leaf diseases in robusta coffee leaves and determine the classification. The application of machine learning-based image processing using the support vector machine (SVM) classification method based on the gray-level co-occurrence matrix (GLCM) feature extraction can be the proposed solution. The preprocessing must precede the processing stage for easier analysis of the image’s quality. Then, the k-means clustering segmentation process was conducted to distinguish leaf parts affected by leaf spot and rust from those unaffected. The GLCM method was employed as the feature extraction based on the angular second moment (ASM) or energy features, contrasts, correlations, inverse different moment (IDM) or homogeneities, and entropy with angles of 0°, 45°, 90°, and 135°, as well as inter-pixel distances of 1 until 3. The classification was done with the SVM method using the linear, polynomial, and radial basis function (RBF) Gaussian kernels. This research used leaf spot and rust images, with training and test data of 320 and 80 images, respectively. The RBF Gaussian achieved the best test results with the best accuracy of 97.5%, precision of 95.24%, recall of 100%, and F1-score of 97.56%.
Co-Authors Agus Supriyanto Oky Dwi Nurhayati