Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Pendas : Jurnah Ilmiah Pendidikan Dasar Journal Of Information And Technology Unimor (JITU)
Muhammad Akhyar, Ramaulvi
Unknown Affiliation
Computer Science & IT Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analisis Pengaruh Data Augmentasi Pada Klasifikasi Tenun Menggunakan Deep Learning Berbasis Convolutional Neural Network: Analisis Pengaruh Data Augmentasi Pada Klasifikasi Tenun Menggunakan Deep Learning Berbasis Convolutional Neural Network Baso, Budiman; Risald, Risald; Muhammad Akhyar, Ramaulvi
Journal of Information and Technology Vol. 5 No. 1 (2025): Journal of Information and Technology Unimor (JITU)
Publisher : Department of Information Technology, Universitas Timor, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32938/jitu.v5i1.9209

Abstract

This research develops a classification model of Timorese weaving motifs using Deep Learning method based on Convolutional Neural Network (CNN). Timor's diverse weaving motifs reflect the richness of local culture, but manual classification takes a long time and is prone to subjectivity. To improve model performance, Data Augmentation techniques, such as flipping, rotation, and zooming,, are applied to enrich the variety of pre-processed Timor weaving image datasets. In addition, the CNN model was developed using Transfer Learning techniques to improve training efficiency. Experimental results show that CNN without augmentation achieves 95.00% accuracy, 95.00% precision, 95.08% recall, and 95.04% F1-score, with a computation time of 2.37 minutes at 30 epochs. Meanwhile, applying Data Augmentation increased the model accuracy to 96.66%, precision 96.66%, recall 96.87%, and F1-score 96.77%, and reduced the computation time to 2.11 minutes. Analysis of the effect of augmentation data shows that increasing the variety of images contributes to the improvement of model generalization. Therefore, the use of CNN with Data Augmentation is a more optimal solution in the classification of Timorese weaving motifs. This research has the potential to support cultural preservation as well as the development of an artificial intelligence-based weaving motif identification system.
Implementasi Deep Learning Berbasis Convolutional Neural Network untuk Klasifikasi Motif Tenun Timor Baso, Budiman; Muhammad Akhyar, Ramaulvi
Journal of Information and Technology Vol. 4 No. 1 (2024): Journal of Information and Technology Unimor (JITU)
Publisher : Department of Information Technology, Universitas Timor, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32938/jitu.v4i1.7971

Abstract

This research develops a classification model for Timorese weaving motifs, including Buna, Kaimafafa, Kemak, and Nunkolo motifs, using Deep Learning method based on Convolutional Neural Network (CNN). Timor's diverse weaving motifs reflect the richness of the local culture, but manual classification is often time-consuming. To overcome this challenge, we applied CNN with transfer learning techniques to a dataset of pre-processed Timorese weaving images. Based on the experimental results, the developed model achieved an accuracy of 95.00% on the test data with the use of 20 epochs, demonstrating the effectiveness of CNN in classifying weaving motifs automatically and efficiently. This research has the potential to support cultural preservation and the development of the weaving industry through technology-based practical applications that are optimal in terms of performance and computational efficiency.
RANCANG BANGUN WEBSITE PROFIL SEKOLAH MENGGUNAKAN FRAMEWORK LARAVEL PADA SDN 008 LOA JANAN ILIR Aswad Nugraha, Muh; Muhammad Akhyar, Ramaulvi
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 03 (2026): Volume 11 No. 03, September 2026 Release
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i03.56285

Abstract

The development of information technology requires schools to provide integrated and easily accessible information media. SDN 008 Loa Janan Ilir still delivers information through separate media, resulting in school information not being centrally documented. This study aims to develop a Laravel-based school profile website and evaluate its feasibility based on functionality and Usability aspects. The research employed the Research and Development (R&D) method with the Waterfall model, including requirements analysis, design, implementation, testing, and maintenance. The website was developed using Laravel 12 and MySQL. Functionality testing was conducted through Black Box Testing by three engineering experts based on the ISO 9126 standard, while Usability testing involved 25 respondents consisting of teachers and community members. The results showed that the website was successfully developed according to user requirements. A functionality score of 1.00 and a Usability score of 89.46% indicate that the website is highly feasible as an official school information medium.
PERBANDINGAN MEDIA PEMBELAJARAN WORDWALL DAN QUIZIZZ TERHADAP HASIL BELAJAR MATERI JARINGAN KOMPUTER Al Munawarah, Ainul; Muhammad Akhyar, Ramaulvi
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 03 (2026): Volume 11 No. 03, September 2026 Processed
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i03.61336

Abstract

The use of digital learning media is one of the options in improving the quality of learning in informatics subjects. This study aims to compare student learning outcomes after using Wordwall and Quizizz interactive media  on computer network materials. This study applies a quantitative approach with experimental methods and repeated measurement designs. The research sample amounted to 43 students of classes VIII A and VIII B SMPN 6 Loa Janan who were selected using saturated sampling techniques (total sampling). All students received learning using both media in turn, then the learning results were analyzed using the Wilcoxon Signed-Rank Test with the help of SPSS software version 27 because the data was not distributed normally. The results showed that the average learning outcome using Wordwall media  was 83.53, while using Quizizz media  was 80.56. The results of the Wilcoxon Signed-Rank Test obtained an Asymp score. Sig. (2-tailed) is 0.036(<0.05), so there is a significant difference between the use of Wordwall and Quizizz media on student learning outcomes. The effect size calculation  obtained a value of 0.319 which is in the medium category. Based on the comparison of average scores, Wordwall media  produces higher learning outcomes than Quizizz media  on computer network materials.
Co-Authors Al Munawarah, Ainul Aswad Nugraha, Muh Baso, Budiman