Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Multimedia Jurnal Teknologi Informasi, Komputer, dan Aplikasinya (JTIKA )
Agustini, Latifa Zahra
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

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

Found 2 Documents
Search

 1 
Development of an AR-Based Solar System Flashcard Learning Media for Elementary Students Using the MDLC Method Rassy, Regania Pasca; Nurrahmadayeni, Nurrahmadayeni; Raihan, Muhammad Dzulhi; Agustini, Latifa Zahra; Mahdi, Anandi Neina Aeyska; Octariana, Ghina Briliana Fatin; Az Zahro, Luthfiyyah
Jurnal Teknologi Informasi dan Multimedia Vol. 8 No. 2 (2026): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v8i2.917

Abstract

Understanding the solar system remains challenging for elementary school students due to the abstract, spatial, and three-dimensional nature of astronomical concepts, which are often difficult to convey through conventional learning media. In response to this challenge, this study aims to develop and evaluate an Augmented Reality (AR)–based solar system flashcard learning media to support interactive and meaningful science learning at the elementary level. The learning media was developed using the Multimedia Development Life Cycle (MDLC) method, which consists of concept formulation, design, material collection, assembly, testing, and distribution stages. The AR application integrates three-dimensional planetary visualizations with flashcards to facili-tate concrete representation of abstract concepts and enhance student engagement. The evaluation focused on usability and learning support through User Acceptance Testing (UAT), involving 10 elementary school students and employing a 3-point Likert scale questionnaire. The results indi-cate that the AR-based flashcard media is easy to use, functions reliably, and effectively supports students’ understanding of solar system concepts. Students reported positive experiences in in-teracting with the learning media, suggesting its potential to improve motivation and conceptual comprehension in science learning. This study contributes to the development of innovative digi-tal learning media that promotes inclusive and quality education by integrating emerging tech-nologies into early science instruction. In alignment with Sustainable Development Goal (SDG) 4, the proposed AR-based learning media supports equitable access to engaging educational re-sources and enhances learning quality through interactive, technology-enabled instruction for elementary students.
EYE DISEASE CLASSIFICATION USING DEEP LEARNING: A COMPARATIVE STUDY OF MOBILENETV2, XCEPTION, AND EFFICIENTNET-B0 Agustini, Latifa Zahra; Bimantoro, Fitri; Dwiyansaputra, Ramaditia
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 8 No 1 (2026): Maret 2026
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v8i1.518

Abstract

This study presents a comparative analysis of three convolutional neural network (CNN) architectures—MobileNetV2, Xception, and EfficientNet-B0—for classifying retinal fundus images into four categories: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. Using a dataset of 4,217 images, the models were trained with transfer learning, image augmentation, and regularization techniques, and evaluated through 5-fold cross-validation. EfficientNet-B0 achieved the highest mean accuracy (0.85) and demonstrated stable performance across all metrics, while MobileNetV2 provided competitive accuracy with lower computational requirements, making it suitable for resource-limited environments. Xception showed the lowest and least stable performance, indicating a higher tendency to overfit. External validation with clinical images revealed a significant drop in accuracy for all models, highlighting challenges related to domain shift and limited generalization. Grad-CAM analysis also showed difficulties in detecting subtle pathological features in Diabetic Retinopathy and Glaucoma. The study is limited by the small dataset size, reliance on a single data source, and the absence of additional clinical information. Future work should incorporate larger and more diverse datasets, apply domain adaptation strategies, and integrate multimodal clinical data to enhance robustness and clinical applicability.
Co-Authors Az Zahro, Luthfiyyah Dwiyansaputra, Ramaditia Fitri Bimantoro Mahdi, Anandi Neina Aeyska Nurrahmadayeni, Nurrahmadayeni Octariana, Ghina Briliana Fatin Raihan, Muhammad Dzulhi Rassy, Regania Pasca