Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization Jurnal Pengabdian UNDIKMA
Jefri, Muhammad Rivaldi
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Nursing Public Health Social Sciences Other

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

Found 2 Documents
Search

 1 
Multi-Head Attention in Residual Networks to Improve Coral Reef Structure Classification Nuranti, Eka Qadri; Intizhami, Naili Suri; Tassakka, Muhammad Irpan Sejati; Areni, Intan Sari; Al Ghozy, Osama Iyad; Jefri, Muhammad Rivaldi
JOIV : International Journal on Informatics Visualization Vol 8, No 2 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.2.2392

Abstract

Residual Networks (ResNet) mark a crucial advancement in convolutional neural network architecture, effectively tackling challenges like vanishing gradients for improved pattern detection in various image classification tasks. This study introduces a novel adaptation of the ResNet50 architecture that integrates a multi-head attention mechanism (MHA), coined MHA-ResNet50, for discerning coral reef structures within images. Strategic modifications are applied to the input of each stage, leading to the development of an MHA block, which is augmented by separable convolution. The deliberate inclusion of the MHA block at various stages in identity-block Resnet50, in adherence to multiscale gate principles, precedes its traversal through fully connected layers. Furthermore, we implemented the Stratified K-fold concept to ensure that each fold has a comparable proportion of each class. We successfully assessed the efficacy of the MHA-Resnet50 model in several MHA-block placement scenarios and saw improvements in the accuracy of coral reef structure predictions. The most optimal results were achieved by incorporating four attention blocks (MHA-ResNet50-4), yielding an accuracy rate of 85.23% in recognition of coral structure images, comprising a mere 409 images. This model showcases adaptability to small datasets while delivering commendable performance. The ResNet50 architecture undergoes enhancement in our proposed model by integrating multi-head attention, separable convolution, and multiscale gate principles. The MHA-ResNet50 model substantially advances accurately predicting coral reef structures, demonstrating adaptability to limited datasets. Future lines of this research involve digging deeper into the model design and using more significant amounts and classes of data to strengthen a more comprehensive range of generalizations.
Implementasi Sistem Monitoring Pembangunan Berbasis Kolaborasi untuk Optimalisasi Tata Kelola Pemerintah Kota Parepare Nuranti, Eka Qadri; Intizhami, Naili Suri; Tunnisa, Khaera; Mar’atuttahirah; Jefri, Muhammad Rivaldi; Anugrah, Muhammad; Alfian, Muhammad; Hakim, Lukman; Alfatih, Muhammad Aldi; Palaloi, Rahmat Eka Putra R
Jurnal Pengabdian UNDIKMA Vol. 7 No. 2 (2026): May (IN PRESS)
Publisher : LPPM Universitas Pendidikan Mandalika (UNDIKMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jpu.v7i2.19958

Abstract

This community service program aims to implement a Development Monitoring System based on collaboration between academics and the local government in order to improve reporting efficiency, data consistency, and information validity, while strengthening the capacity of government officials to support transparent and accountable governance. The program involved 14 officials from the Regional Development Planning Agency (Bappeda) of Parepare City. The implementation methods included needs analysis, system design, implementation, as well as training and technical assistance. Evaluation was conducted through pre-test and post-test assessments using the Quizizz application and user satisfaction questionnaires. The results showed an improvement in participants’ understanding, particularly in technical aspects, with an accuracy increase of 25% (from 64% to 89%). In addition, the level of user satisfaction was high, with the ease-of-use score reaching 4.50 out of 5, indicating that the system was easy to operate and well accepted by users. This program highlights the importance of collaboration between academics and local government in realizing data-driven development governance and has the potential to be further developed through integration with other systems, such as the Regional Innovation System and the Performance Indicator System.
Co-Authors Al Ghozy, Osama Iyad Alfatih, Muhammad Aldi Areni, Intan Sari Eka Qadri Nuranti Khaera Tunnisa, Khaera Lukman Hakim Mar’atuttahirah Muhammad Alfian, Muhammad Muhammad Anugrah, Muhammad Naili Suri Intizhami Palaloi, Rahmat Eka Putra R Tassakka, Muhammad Irpan Sejati