Robust coffee plant disease classification using deep learning and advanced feature engineering techniques
PeerJ Computer Science · 09.12.2025 · 11 · e3386
DOI: 10.7717/peerj-cs.3386 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 09.12.2025. Verfasst von Hanin Ardah und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah bint Abdulrahman University Researchers Riyadh, Saudi Arabia.
Abstract (Originalsprache)
Coffee, the world’s most traded tropical crop, is vital to the economies of many producing countries. However, coffee leaf diseases pose a serious threat to coffee quality and sustainable production. Deep learning has shown strong performance in plant disease identification through automatic image classification. Nevertheless, reliance on a single convolutional neural networks (CNNs) architecture restricts feature variability and real-world generalization. Moreover, limited work has systematically combined feature selection/reduction with CNNs, which constrains the advancement of hybrid models capable of capturing complementary features while ensuring computational efficiency without accuracy loss. This article presents an enhanced deep learning-based framework for coffee disease classification incorporating a hybrid strategy that integrates CNNs and advanced feature selection algorithms. GoogLeNet and ResNet18 are paired for complementary feature extraction, Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) are employed for dimensionality reduction, and ANOVA and Chi-square are applied to select the most informative features. An Adam optimizer (learning rate = 0.001, batch size = 20, epochs = 50) with early stopping is used for training. Experiments on the BRACOL dataset achieved 99.78% accuracy, with precision, recall, and F1-score all exceeding 99% across classes. To the best of our knowledge, this study systematically integrates GoogLeNet and ResNet18 with PCA/SVD dimensionality reduction and analysis of variance (ANOVA)/Chi-square feature selection, for coffee disease classification, thereby addressing a key gap in prior research.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
- Computer Science and Engineering Department, JNTUH University College of Engineering, Science & Technology Hyderabad, Hyderabad, Telangana, India.
- Computer Science Department, Faculty of Computers and Artificial Intelligence, Sohag University, Sohag, Egypt.
- College of Engineer and Computer Science, Jazan University, Jazan, Saudi Arabia.
- Information System Department, Obour Institutes for Obour High Institute for Management and Computers and Information Systems, Cairo, Egypt.
ORCID-Profile: Hanin Ardah, Doaa Trabay
Förderung
- Princess Nourah bint Abdulrahman University Researchers Riyadh, Saudi Arabia
Zitieren
APA
Ardah, H., Alrahhal, M., M Abd-Elhafiez, W., & Trabay, D. (2025). Robust coffee plant disease classification using deep learning and advanced feature engineering techniques. PeerJ Computer Science, 11, e3386. https://doi.org/10.7717/peerj-cs.3386
Vancouver
Ardah H, Alrahhal M, M Abd-Elhafiez W, Trabay D. Robust coffee plant disease classification using deep learning and advanced feature engineering techniques. PeerJ Computer Science. 2025;11:e3386. doi:10.7717/peerj-cs.3386
BibTeX
@article{Ardah2025,
author = {Ardah, Hanin and Alrahhal, Maher and M Abd-Elhafiez, Walaa and Trabay, Doaa},
title = {Robust coffee plant disease classification using deep learning and advanced feature engineering techniques},
journal = {PeerJ Computer Science},
year = {2025},
volume = {11},
pages = {e3386},
doi = {10.7717/peerj-cs.3386}
}
EUVIMED