Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JISKa (Jurnal Informatika Sunan Kalijaga)
Okta Qomaruddin Aziz
Universitas Islam Negeri Maulana Malik Ibrahim
Computer Science & IT Electrical & Electronics Engineering Library & Information Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Pengaruh Orientasi Citra MRI pada Klasifikasi Tumor Otak Berbasis GLCM dan SVM Yoza Setya Febriyanti; Okta Qomaruddin Aziz; Suhartono Suhartono
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 2 (2026): May 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.5935

Abstract

Brain tumors are a global health problem, ranking 12th as a cause of death. MRI is used in the diagnosis of brain tumors because of its ability to display soft tissue structures in detail, but manual interpretation of MRI images by radiologists is still subjective. Therefore, a more objective computer-based classification approach is needed. One factor that could potentially affect classification performance is the difference in MRI image orientation, namely axial, sagittal, and coronal. This study aims to analyze the effect of MRI image orientation on GLCM and SVM-based brain tumor classification. The preprocessing stage includes cropping, noise reduction, and resizing. Feature extraction was performed using GLCM with distance d = 1 at angles of 0°, 45°, 90°, and 135° with contrast, correlation, energy, and homogeneity features. Classification was performed using SVM with Linear, Polynomial, RBF, and Sigmoid kernels. The test results show that the axial orientation produces the highest accuracy of 78% with the Linear kernel, the sagittal orientation achieves an accuracy of 83% with the Polynomial kernel, and the coronal orientation provides the highest accuracy of 86% with the RBF kernel. These findings indicate that the orientation of MRI images affects the performance of texture-based brain tumor classification.
Klasifikasi Penyakit Mata Berdasarkan Citra Fundus Menggunakan Metode Multi-Layer Perceptron Laudza Atsila Prasetyo; Okta Qomaruddin Aziz; Tri Mukti Lestari
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 2 (2026): May 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.6022

Abstract

This research aims to evaluate the performance of the Multi-Layer Perceptron (MLP) for classifying eye diseases from fundus images in the ODIR dataset, which comprises four classes: Normal, Diabetic, Glaucoma, and Cataract. The methodology includes feature extraction using GLCM and Gabor, data pre-processing through cleaning, augmentation, and undersampling, and testing 16 model scenarios with variations in the number of hidden layers (2 and 3) and neuron configurations. The results show that data balance and dataset size are the most influential factors affecting model performance, with the best results achieved through the combination of undersampling and augmentation. The optimal architecture was obtained with the 64–32-neuron configuration, yielding a mean accuracy of 73.06%. Overall, this study concludes that combining a balanced dataset with a proportional MLP architecture significantly improves the model’s ability to classify eye diseases from fundus images.
Co-Authors Laudza Atsila Prasetyo Suhartono Suhartono Tri Mukti Lestari Yoza Setya Febriyanti