Claim Missing Document
Check
Articles

Found 2 Documents
Search

Comparison of Standard and Squeeze-and-Excitation Enhanced DenseNet Architectures for Tomato Leaf Disease Classification Using Data Augmentation Andriani, Tuti; Nainggolan, Irfan
Bahasa Indonesia Vol 17 No 08 (2025): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v17i08.429

Abstract

The advancement of deep learning has significantly improved the automation of plant disease detection through image classification. This study compares the performance of standard DenseNet121 and an enhanced version incorporating Squeeze-and-Excitation (SE) blocks for classifying tomato leaf diseases. A dataset derived from PlantVillage was used, covering multiple disease categories and healthy leaves. To improve generalization, extensive data augmentation techniques were applied. Both architectures were implemented and trained using PyTorch, with evaluation metrics including accuracy, precision, recall, F1-score, and inference time. The experimental results demonstrate that DenseNet121-SE significantly outperforms the standard DenseNet121, achieving a classification accuracy of 99.00%. The integration of SE blocks allows the model to recalibrate channel-wise features adaptively, enhancing sensitivity to important patterns while maintaining computational efficiency. This study highlights the effectiveness of attention mechanisms and data augmentation in improving classification performance and supports their practical application in intelligent agriculture systems.
Decision Support System for Selecting College Majors Based on Student Interests and Talents Using the SAW Method Nainggolan, Irfan; Simangunsong, Suhendra
Bahasa Indonesia Vol 17 No 08 (2025): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v17i08.430

Abstract

This article formulates and demonstrates a Decision Support System (DSS) model for selecting a college major by placing interest and talent/aptitude as the core criteria using the Simple Additive Weighting (SAW) method. The fully documented methodology includes criteria definition, normalization procedure (benefit/cost), weighting, score calculation, implementation pseudo-code, and weight sensitivity analysis. An illustrative study using a simulated dataset with five alternative study programs and six criteria shows consistent and transparent ranking for counselors and students. The results confirm the significance of interest-aptitude integration in recommendations, while demonstrating decision stability under moderate weight changes. Practical contributions include workflow design and functional specifications for web/desktop applications; further development is directed at AHP–SAW and fuzzy-SAW.