Multi-Class Supervised Learning for Accurate Leaf Fungus Quantification Using Simplified Integrated CNN-SVM for Leaf Fungus Quantification (SICLFQ)

View at publisher Summarise with VIRAT
Authors: C. Naga Pradeep Kumar, K. Govardhan Reddy
Cited by: 0
References: 21

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

$A B S T R A C T$: For quantitative measurement of leaf fungus, the research discloses an innovative algorithm called Simplified Integrated CNN-SVM for Leaf Fungus Quantification (SICLFQ) that cleverly hybridizes Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) to figure out the amount of fungus on the leaves accurately. The article notes that fungi on leaves, their symptoms, and the necessity of accurate fungal quantification are some of the scientific requirements addressed by the study. Besides, it points to the inaccuracies of traditional methods and, machine-learning techniques, vigorously, advocates the use of advanced. SICLFQ is a multi-class supervised learning model, wherein CNNs are used for feature extraction and SVMs for classification, thus, leading to a higher result than the present algorithms. Its thorough method goes beyond just dataset gathering, preprocessing, environment setup, algorithm implementation, and detailed performance evaluation and, consequently, it is accompanied by a large collection of annotated leaf images. Comparison experiments demonstrate that SICLFQ outperforms CNN-based, SVM-based, and Random Forest-based algorithms in terms of accuracy, precision, recall, and$\mathbf{F 1}$score, and the graphs make it easy to grasp the findings. Far from just being a paper that introduces a groundbreaking strategy for plant disease management, it actually serves as a platform for more innovations that, in the end, will result in healthier crops and sustainable agricultural practices.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Leaf Properties and Growth Measurement

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1–9
Publication date
21 January 2026
Language
EN