Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JURNAL INSTEK (Informatika Sains dan Teknologi) Journal Medical Informatics Technology
Malau, Fransiscus Rolanda
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Dentistry Electrical & Electronics Engineering Engineering Medicine & Pharmacology Public Health

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

Found 2 Documents
Search

 1 
OPTIMIZING CNN PERFORMANCE FOR AI-GENERATED IMAGE CLASSIFICATION: A COMPARATIVE STUDY OF ARCHITECTURES AND OPTIMIZERS USING K-FOLD CROSS-VALIDATION Malau, Fransiscus Rolanda
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 9 No 2 (2024): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v9i2.54193

Abstract

This study investigates CNN optimization for classifying AI-generated images. Using the CIFAKE dataset (60,000 real and 60,000 AI-generated images), we evaluated four CNN configurations with varying complexity and four optimization algorithms through 5-fold cross-validation. Our findings show Configuration 4 (4 Conv, 2 MaxPool) with Adam optimizer achieved the highest validation accuracy (0.8368±0.0135). Adam demonstrated consistent performance across architectures, while SGD showed strong but variable results improving with model complexity. Adagrad and Adadelta consistently underperformed. The final model achieved 85.28% test accuracy with balanced precision (0.8531) and recall (0.8528). Results indicate more complex architectures combined with adaptive optimizers like Adam provide superior performance for AI-generated image classification, with the balance between model complexity and optimizer selection being crucial. The consistent performance across real and fake categories demonstrates this approach's robustness for deepfake detection applications.
Measuring User Acceptance Of ALODOKTER Application With Technology Acceptance Model To Enhance Health Service Quality Malau, Fransiscus Rolanda; Sakti, Ichtiar Akbar
Journal Medical Informatics Technology Volume 3 No. 3, September 2025
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v3i3.47

Abstract

ALODOKTER is one quickly evolving application in the healthcare services sector. The purpose of this application is to help medical professionals carry out their jobs more effectively by giving the community rapid and easy access to healthcare services. This study aims to measure user acceptance of the ALODOKTER application using the Technology Acceptance Model (TAM) approach to improve the use and quality of health services. A survey method with a quantitative approach was employed to analyze perceived ease of use (PEU), perceived usefulness (PU), attitude towards use (ATU), behavioral intention to use (BIU), and actual use (AU) of the application. The study involved 41 respondents from various demographic backgrounds. Results show significant relationships between user perception variables, attitudes, and actual use. Correlation analysis revealed strong relationships between PEU, PU, and ATU, with a very strong correlation between ATU and BIU. Linear regression analysis indicated that BIU was the strongest predictor of actual use of the app (β = 1.066, p < 0.01), followed by PU (β = 0.628, p < 0.01). The regression model explained 38.7% of the variance in actual use. Cronbach's Alpha coefficients for all scales exceeded 0.9, indicating high reliability of the instruments used. This research suggests that ALODOKTER developers should focus on enhancing the perceived usefulness and ease of use of the application to increase acceptance and use. The study's limitations include a small sample size and reliance on self-reporting, suggesting the need for further research with larger samples and more diverse methods.
Co-Authors Sakti, Ichtiar Akbar