Claim Missing Document
Check
Articles

Found 2 Documents
Search

Comparative analysis of convolutional neural network architectures for guava disease classification Rahman Wahabi Hasibuan; Muhammad Amin Rais; Mutiara Akbar Nasution
Jurnal Sains, Teknologi & Komputer Vol. 3 No. 3 (2026): Jurnal Sains, Teknologi & Komputer (SAINTEK)
Publisher : Lembaga Riset Mutiara Akbar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56495/saintek.v3i3.1302

Abstract

This study aims to compare the performance of two Convolutional Neural Network (CNN) architectures, EfficientNetB0 and EfficientNetV2-S, in classifying guava (Psidium guajava L.) conditions based on digital images. The dataset consists of three classes: anthracnose, fruit fly infestation, and healthy fruits. Class imbalance was addressed using an undersampling technique, while both models were developed using a transfer learning approach with ImageNet pre-trained weights and trained for 30 epochs. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results showed that EfficientNetB0 achieved a validation accuracy of 99.49% with a loss of 0.0124, whereas EfficientNetV2-S achieved a validation accuracy of 94.17% with a loss of 0.2153. The classification report further showed that EfficientNetB0 achieved F1-scores ranging from 0.99 to 1.00 across the three classes, while EfficientNetV2-S achieved F1-scores ranging from 0.92 to 0.96. Based on these results, EfficientNetB0 demonstrated higher classification performance than EfficientNetV2-S on the dataset and training configuration used in this study.
Design and implementation of a reusable component-based architecture for learning media Muhammad Amin Rais; Mutiara Akbar Nasution
Jurnal Sains, Teknologi & Komputer Vol. 3 No. 2 (2026): Jurnal Sains, Teknologi & Komputer (SAINTEK)
Publisher : Lembaga Riset Mutiara Akbar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56495/saintek.v3i2.1675

Abstract

The development of digital learning media often requires repeated implementation of similar features such as quiz systems, video players, module navigation, and progress trackers in different applications. This study proposes a reusable prefab-based architecture on the Unity platform by applying the principles of Component-Based Software Engineering (CBSE). The developed architecture consists of seven core reusable components: Lobby, Module Layout, Material, Video Player, Quiz, Progress Tracker, and Main Setting Component. The study uses a Research and Development (R&D) approach with a modified ADDIE model and is implemented using Unity 2022 LTS and the C# programming language. Evaluation is carried out through the implementation of component libraries in five different learning media applications. The results show that most components have a high reuse ratio, a maintainability index above 70, and low coupling dependencies, thus supporting system modularity and reusability. This study shows that a reusable prefab-based architecture can be an effective solution in the development of modular, flexible, and scalable digital learning media.