Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Community Development Engineering Science Letter
Agil Rahmat
Institut Teknologi Garut
Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Nursing Public Health Social Sciences

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

Found 2 Documents
Search

 1 
Sosialisasi Pencegahan Hoax dan Ujaran Kebencian di Madrasah Aliyah Swasta Muhammadiyah Bayongbong Eri Satria; Agil Rahmat; Zatnika Insan Kamil; Muhammad Alfi Faishal; Gina Suciyana; Garnis Kirani
Journal of Community Development Vol. 5 No. 2 (2024): December
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v5i2.1370

Abstract

Hate speech and hoaxes have become significant problems in the current era of democracy and digitalization. Advances in Information and Communication Technology (ICT), especially social media, have facilitated the rapid and widespread spread of hoaxes and hate speech in Indonesia. The main problem in dealing with hoaxes is the lack of critical thinking about the information received. Therefore, prevention of hoaxes through education is important. Education can help people detect hoax news and reduce its spread. To conduct this education, the research method used is socialization and education at MAS Muhammadiyah Bayongbong school, especially at the high school level. This activity involved students, partners, and participants. The stages of the activity include surveys, delivery of material on hoaxes and education, and practice using ICT. This activity showed that some participants experienced an increase in knowledge after participating in the socialization. However, there were some difficulties in answering the test questions given. In addition, analysis of the average score of the questions showed an increase from pre-test to post-test. However, there are some materials that are still an obstacle for participants in understanding them.
Optimization of Malaria Cell Image Classification Using Pretrained Resnet50 Architecture with Data Augmentation and Fine-Tuning Asri Mulyani; Dede Kurniadi; Agil Rahmat
Engineering Science Letter Vol. 4 No. 02 (2025): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.001244

Abstract

Malaria remains a significant health concern, particularly in tropical regions such as Indonesia, where timely and accurate diagnosis is crucial for reducing transmission and mortality. Conventional diagnosis through microscopic examination is labor-intensive, time-consuming, and highly dependent on expert availability. This study proposes an automated malaria cell image classification model using a deep learning approach based on the pretrained ResNet50 architecture. The research framework adopts the SEMMA (Sample, Explore, Modify, Model, Assess) methodology to structure the development workflow. A total of 27,558 labeled blood cell images comprising two balanced classes, Parasitized and Uninfected, were used for training and evaluation. Two model configurations were tested: a baseline model without data augmentation or fine-tuning, and an optimized model that integrates both. Augmentation techniques such as rotation, flipping, shearing, zoom, and brightness adjustment were applied to increase data diversity, while fine-tuning involved unfreezing the last 20 layers of ResNet50 to adapt pretrained features to the malaria domain. Performance was evaluated using accuracy, precision, recall, F1-score, loss, and AUC-ROC. The optimized model achieved 97.63% accuracy, 0.996 AUC-ROC, and 0.2472 loss, outperforming the baseline accuracy of 92.84%. An ablation study analyzed the individual contributions of augmentation and fine-tuning, showing that both techniques play complementary roles, with fine-tuning having the greater impact. A McNemar test confirmed that the improvements were statistically significant (p < 0.05). These findings demonstrate that the optimized ResNet50 model is effective for malaria detection and holds promise for integration into real-time diagnostic systems in resource-constrained environments.
Co-Authors Asri Mulyani Dede Kurniadi Eri Satria Garnis Kirani Gina Suciyana Muhammad Alfi Faishal Zatnika Insan Kamil