Article Per Year (5 Year)
p-Index From 2021 - 2026
1.679
P-Index
This Author published in this journals
All Journal Jurnal Sarjana Teknik Informatika Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal Gramatika Buletin Ilmiah Sarjana Teknik Elektro Mobile and Forensics JOURNAL OF INFORMATION SYSTEM MANAGEMENT (JOISM) Buletin Sistem Informasi dan Teknologi Islam Jurnal Gramatika: Jurnal Penelitian Pendidikan Bahasa dan Sastra Indonesia
Nuril Anwar
Universitas Ahmad Dahlan
Humanities Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Library & Information Science Neuroscience

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Image Forensics Using Error Level Analysis and Block Matching Methods Iis Sudianto; Nuril Anwar
Mobile and Forensics Vol. 6 No. 2 (2024)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v6i2.5719

Abstract

The development of image editing tools today makes everyone able to manipulate images easily so that many images are doubtful of their authenticity. The current image can be used as evidence in a legal case in court. The authenticity of the image is a topic that many have tried to solve various studies. This study discusses the authenticity of the image using the Error Level Analysis (ELA) method to determine the authenticity of the image, especially in the JPEG image. Block Matching is used in the process of dividing an image into several square or block parts. The ELA method has been successfully implemented with 95% image compression resulting in MSE and PSNR values ​​in distinguishing the edited image. The average MSE is 23.8 dB and the average PSNR is 34.47 dB. Block Matching results as a whole show that the pixel value for x values ​​that reach 30 there are 9 images, x values ​​that reach 24 there are 9 images, x values ​​that reach 23 there are 1 image, and for x values ​​that reach 19 there is 1 image. The result of pixel (y) of all images exceeds the value of 12 which in pixel (y) undergoes many changes marked by the presence of white spots.
Geographic-Origin Music Classification from Numerical Audio Features: Integrating Unsupervised Clustering with Supervised Models Andri Pranolo; Sularso Sularso; Nuril Anwar; Agung Bella Utama Putra; Aji Prasetya Wibawa; Shoffan Saifullah; Rafał Dreżewski; Zalik Nuryana; Tri Andi
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.13400

Abstract

Classifying the geographic origin of music is a relevant task in music information retrieval, yet most studies have focused on genre or style recognition rather than regional origin. This study evaluates Support Vector Machine (SVM) and Convolutional Neural Network (CNN) models on the UCI Geographical Origin of Music dataset (1,059 tracks from 33 non-Western regions) using numerical audio features. To incorporate latent structure, we first applied K-means clustering with the optimal number of clusters (k=2) determined by the Elbow and Silhouette methods. The cluster assignments were used as auxiliary signals for training, while evaluation relied on the true region labels. Classification performance was assessed with Accuracy, Precision, Recall, and F1-score. Results show that SVM achieved 99.53% accuracy (95% CI: 97.38–99.92%), while CNN reached 98.58% accuracy (95% CI: 95.92–99.52%); Precision, Recall, and F1 mirrored these values. The differences confirm SVM’s superior performance on this dataset, though the near-perfect scores also suggest strong separability in the feature space and potential risks of overfitting. Learning-curve analysis indicated stable training, and cluster supervision provided small but consistent benefits. Overall, SVM remains a reliable baseline for tabular music features, while CNNs may require spectro-temporal representations to leverage their full potential. Future work should validate these findings across multiple datasets, apply cross-validation with statistical significance testing, and explore hybrid deep models for broader generalization.
Co-Authors Agung Bella Utama Putra Aji Prasetya Wibawa Akbar Ramadhan Andri Pranolo Iis Sudianto Imam Riadi Lucky Barga Aretama Luthfi Amalia Zain M. Ardi Kurniawan Mohammad Argi Arifandi Mu'Minin Mu'Minin Muhammad Ilham Azmi Murein Miksa Mardhia Rachmad Nur Fauzi Raden Hario Wahyu Murti Rafał Dreżewski Saifullah, Shoffan Sularso, Sularso Taufiq Ismail Tri Andi Wirawati, Denik Yosi Wulandari Zalik Nuryana