VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection

Convolution Neural Networks (CNN) are best in their ability to detect rice diseases but still face challenges in generalizing equally well for all classes of disease in multiclass classification. Detecting rice crop disease like sheath rot is still challenging due to unavailability of dataset and in...

Full description

Saved in:
Bibliographic Details
Main Authors: Sanam Salman Kazi, Bhakti Palkar, Dhirendra Mishra
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:MethodsX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2215016125003954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849397534112350208
author Sanam Salman Kazi
Bhakti Palkar
Dhirendra Mishra
author_facet Sanam Salman Kazi
Bhakti Palkar
Dhirendra Mishra
author_sort Sanam Salman Kazi
collection DOAJ
description Convolution Neural Networks (CNN) are best in their ability to detect rice diseases but still face challenges in generalizing equally well for all classes of disease in multiclass classification. Detecting rice crop disease like sheath rot is still challenging due to unavailability of dataset and intraclass variations in symptoms. Transfer learning models take more resources for execution due to its deep architecture. To conquer these challenges, VCNet, an optimized, novel and efficient multiclass rice crop disease detection framework is proposed. The study focuses on developing a shallow model with deep feature extraction to bring down the computational load with reduced time for training without compromising on any performance parameters. Further the model goes through two level optimization process where optimal hyperparameters identified through experimentation is given as parameters to genetic algorithm for optimization of VCNet during training. Novel dataset containing field images is generated with the help of plant pathologist to improve model capability to identify diseases. Rigorous empirical comparison and evaluation with state-of-the-art models for each class of disease is done to validate proposed technique. VCNet outperforms the existing transfer learning models with training accuracy 99.72 % and testing accuracy 97.71 %. It also requires fewer parameters and takes minimum training time. • The major contribution of this study is the design of an optimized, efficient and enhanced deep learning technique for multiclass rice crop disease detection embracing with batch normalization, dropout and genetic optimization algorithm to improve generalization power and restrict the overlearning capability for seen and unseen data. • Proposed VCNet, a shallow model with deep feature extraction, employs VGG16 layers for initial extraction fused with custom CNN architecture to correctly detect the challenging classes of diseases like sheath rot in multiclass classification. • The most significant observation is that VCNet accurately predicts the rice disease for each class of diseases under study whereas the existing powerful models largely misclassified for some classes of diseases in multiclass classification.
format Article
id doaj-art-d4aa0c1b94b841e4b95339e3039464ad
institution Kabale University
issn 2215-0161
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series MethodsX
spelling doaj-art-d4aa0c1b94b841e4b95339e3039464ad2025-08-20T03:38:58ZengElsevierMethodsX2215-01612025-12-011510355110.1016/j.mex.2025.103551VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detectionSanam Salman Kazi0Bhakti Palkar1Dhirendra Mishra2Department of Computer Engineering, K. J. Somaiya School of Engineering (KJSSE), Somaiya Vidyavihar University, Mumbai, Maharashtra 400077, India; Department of Engineering and Technology, Bharati Vidyapeeth Deemed to be University, Kharghar, Navi Mumbai, Maharashtra 410210, India; Corresponding author.Department of Computer Engineering, K. J. Somaiya School of Engineering (KJSSE), Somaiya Vidyavihar University, Mumbai, Maharashtra 400077, IndiaDepartment of Computer Engineering, SVKM’s NMIMS Deemed to be University Mukesh Patel School of Technology Management & Engineering, Mumbai, 400056, IndiaConvolution Neural Networks (CNN) are best in their ability to detect rice diseases but still face challenges in generalizing equally well for all classes of disease in multiclass classification. Detecting rice crop disease like sheath rot is still challenging due to unavailability of dataset and intraclass variations in symptoms. Transfer learning models take more resources for execution due to its deep architecture. To conquer these challenges, VCNet, an optimized, novel and efficient multiclass rice crop disease detection framework is proposed. The study focuses on developing a shallow model with deep feature extraction to bring down the computational load with reduced time for training without compromising on any performance parameters. Further the model goes through two level optimization process where optimal hyperparameters identified through experimentation is given as parameters to genetic algorithm for optimization of VCNet during training. Novel dataset containing field images is generated with the help of plant pathologist to improve model capability to identify diseases. Rigorous empirical comparison and evaluation with state-of-the-art models for each class of disease is done to validate proposed technique. VCNet outperforms the existing transfer learning models with training accuracy 99.72 % and testing accuracy 97.71 %. It also requires fewer parameters and takes minimum training time. • The major contribution of this study is the design of an optimized, efficient and enhanced deep learning technique for multiclass rice crop disease detection embracing with batch normalization, dropout and genetic optimization algorithm to improve generalization power and restrict the overlearning capability for seen and unseen data. • Proposed VCNet, a shallow model with deep feature extraction, employs VGG16 layers for initial extraction fused with custom CNN architecture to correctly detect the challenging classes of diseases like sheath rot in multiclass classification. • The most significant observation is that VCNet accurately predicts the rice disease for each class of diseases under study whereas the existing powerful models largely misclassified for some classes of diseases in multiclass classification.http://www.sciencedirect.com/science/article/pii/S2215016125003954Deep learningRice disease detectionOptimizationMulticlass ClassificationTransfer learning
spellingShingle Sanam Salman Kazi
Bhakti Palkar
Dhirendra Mishra
VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
MethodsX
Deep learning
Rice disease detection
Optimization
Multiclass Classification
Transfer learning
title VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
title_full VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
title_fullStr VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
title_full_unstemmed VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
title_short VCNet: Optimized Deep Learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
title_sort vcnet optimized deep learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection
topic Deep learning
Rice disease detection
Optimization
Multiclass Classification
Transfer learning
url http://www.sciencedirect.com/science/article/pii/S2215016125003954
work_keys_str_mv AT sanamsalmankazi vcnetoptimizeddeeplearningframeworkwithdeepfeatureextractionandgeneticalgorithmformulticlassricecropdiseasedetection
AT bhaktipalkar vcnetoptimizeddeeplearningframeworkwithdeepfeatureextractionandgeneticalgorithmformulticlassricecropdiseasedetection
AT dhirendramishra vcnetoptimizeddeeplearningframeworkwithdeepfeatureextractionandgeneticalgorithmformulticlassricecropdiseasedetection