A stacking ensemble machine learning based approach for classification of plant diseases through leaf images
Journal Title: Environment Conservation Journal - Year 2024, Vol 25, Issue 3
Abstract
Diseases and pests in plants/crops are major causes of significant agricultural losses with economic, social and ecological impacts. Therefore, there is a need for early identification of plant diseases and pests through automated systems. Recently, machine learning-based methods have become popular in solving agricultural problems such as plant diseases faced by technically-noob farmers. This work proposes a novel method based on stacking ensemble machine learning to detect plant diseases in Uradbean precisely. Two classifiers: support vector machine (SVM), random forest (RF) are trained on a dataset consists of Uradbean infected and healthy leaf images. These classifiers are stacked with logistic regression (LR) classifier. In the diverse ensemble, LR classifier is used as a meta-learner which enhanced the precision of the disease classification. The fuzzy C-Means clustering with particle swarm optimization is used for image segmentation. Haralick, Hu Moments and color histogram methods are used in feature extraction. During the tests, the proposed model is also compared with pre-trained networks: DenseNet-201, ResNet-50, and VGG19. It achieved an impressive classification accuracy of 96.82 % which is higher than the individual classifiers and pre-trained networks. To validate model performance, it is evaluated on a benchmark public dataset consists of Apple leaf images and achieved 98.30% accuracy. It is observed that ensemble method reflects an advantage over individual models in increasing the classification rates and reducing the computational overhead in comparison to pre-trained networks which struggle due to the issues such as irrelevant features, generation of pertinent characteristics, and noise
Authors and Affiliations
Vibhor Kumar Vishnoi, Krishan Kumar, Brajesh Kumar, Rakesh Bhutiani
Keywords
Related Articles
- EP ID EP745672
- DOI https://doi.org/10.36953/ECJ.28742840
- Views 44
- Downloads 0
Study on primary productivity and phytoplankton diversity in different intensive and semi intensive shrimp’s ponds of Dakshina Kannada District, Karnataka
The current study was to examine the significance of primary productivity and phytoplankton density in semi-intensive and intensive shrimp (L. Vannamei) ponds located at Haleyangadi, Mangaluru (Taluk), Dakshina Kannada (...
Studies on pollen performance in some endangered medicinal and aromatic plants of cold desert Ladakh
The study was carried out at the Trans-Himalayan Herbal Garden, located at the National Institute of Sowa Rigpa-Leh, from 2021 to 2023. An assessment of pollen viability was conducted using seven significant medicinal an...
Agronomic biofortification with zinc and iron to enhance nutrient concentrations in mango
Biofortification is a global-scale agricultural approach that can improve human nutrition. Agronomic biofortification is viewed as a quick-fix and supplemental approach. Agronomic biofortification, especially foliar app...
Seasonal occurrence of the shoot fly complex on Rabi sorghum in the Marathwada area of Maharashtra
The present study was conducted to investigate the variety and abundance of shoot flies in the Postgraduate Experimental Field, Department of Agricultural Entomology, College of Agriculture, Latur Campus, Maharashtra, In...
Analysis of the growth profile, biochemical composition and nutrient removal efficacy of Spirulina sp. NCIM 5143
In the present manuscript, the growth profile of the microalgae Spirulina sp. NCIM 5143 was studied. Screening was performed on four commercial media, i.e., blue‒green-11 (BG-11), Bold’s basal medium (BBM), algal cultur...