Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal INOVTEK Polbeng - Seri Informatika
Ery Hartati
Multi Data Palembang University
Computer Science & IT

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

Found 2 Documents
Search

 1 
Enhancing Generalization of Tomato Leaf Disease Classification via TDR Model and Field-Conditioned Data Augmentation Fernando Feliansyah; Ery Hartati
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/tvgfx074

Abstract

Tomato leaf diseases significantly affect agricultural productivity, particularly when detection systems are deployed under real-field conditions characterized by illumination variation, background clutter, and image noise. Although deep learning-based models have achieved high accuracy on laboratory datasets such as PlantVillage, their generalization performance often degrades when applied to real-world environments. This study proposes a lightweight CNN-based tomato leaf disease recognition model, referred to as the TDR-Model, combined with field-conditioned data augmentation strategies. The proposed model integrates MobileNetV3 with Convolutional Block Attention Module (CBAM) and Omni-Dimensional Dynamic Convolution (ODC) to enhance feature representation while maintaining computational efficiency. Field-conditioned augmentation using the Albumentations library to simulate real-world visual variations during training. The model is evaluated on the real-world tomato set consisting of 10 classes and 885 leaf images. Experimental results show that the proposed model achieves an overall test accuracy of 82.94%, with precision, recall, and F1-score of 85.06%, 83.04%, and 83.03%, respectively. Furthermore, the model requires only 3.47 million parameters, 0.23 GFLOPs, and an average inference time of 5.15 ms, making it suitable for real-time and resource-constrained agricultural applications. These results indicate that the proposed approach effectively balances accuracy and efficiency for practical tomato leaf disease detection.
Classification of Tomato Fruit Ripeness Level Using Convolutional Neural Network–Support Vector Machine Based on Digital Image Nelson Saputra Edika; Ery Hartati
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/1r0wh197

Abstract

Tomato ripeness classification is an important task in post-harvest quality management, as the ripeness level directly influences taste, shelf life, and market value. Conventional ripeness assessment methods based on manual visual inspection are inherently subjective and often yield inconsistent results. To address this limitation, this study proposes an image-based tomato ripeness classification model using a hybrid Convolutional Neural Network–Support Vector Machine (CNN–SVM) approach. In the proposed model, a pretrained ResNet-50 architecture is employed as a fixed feature extractor to derive deep visual representations, while a Support Vector Machine with a Radial Basis Function kernel is utilized for final classification. The model is evaluated using a publicly available tomato image dataset, with the analysis limited to unripe and ripe categories. Image preprocessing procedures include resizing, normalization, and data augmentation, followed by an 80:20 train–test split strategy. Experimental results demonstrate that the proposed CNN–SVM model achieves strong and balanced performance, with an accuracy of 96.56%, a weighted precision of 96.80%, a recall of 96.56%, and an F1-score of 96.57%. These findings indicate that integrating deep feature extraction with an SVM classifier provides an effective and robust solution for tomato ripeness classification, particularly under limited data conditions.
Co-Authors Fernando Feliansyah Nelson Saputra Edika