{"title":"ODHEPDC: Optimal Trained Deep Hybrid Ensemble of Classifier for Plant Disease Classification With Improved Deep Fuzzy Clustering","authors":"Ruchi Mittal, Varun Malik, Geetanjali Singla, Amandeep Kaur, Manjinder Singh, Amit Mittal","doi":"10.1111/jph.13388","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Plant diseases are the major factors that affects the quality production as it affects or interrupts the plant's vital functions. The early detection of crop disease could assist farmers in implementing the right preventative measures at the right moment to eradicate it. The main goal of the ODHEPDC (Optimal Trained Deep Hybrid Ensemble of Classifier for Classification of Plant Disease) model is the classification of diseases leaf images. The primary step is to improve the input image by using the MF model to remove the noise. This is considered as the preprocessing step. Improved fuzzy clustering algorithm, leading to the identification of the regions, ROI as well as non-ROI. Next to this, the appropriate features are extracted to define the feature set that includes MPPT feature, PHOG feature, and MTP features as well. However, the curse of dimensionality is the greatest crisis in the classification problem, hence, improved feature level fusion is progressed, which is the simple concatenation of the extracted features. In this, the improved calculation of information gain ensures the reduction and fusion of feature set. The fused features are the inputs to ensemble classification model with the classifiers like CNN, RNN, and DBN classifiers, which gives the classified results. To boost up the performance of classification model, the Deep Maxout model in the ensemble is optimally trained by a new Bald Eagle Search Updated Pelican Optimization (BESUPO) Algorithm via optimal weights tuning as the model determines the final classification outcome. The validation results prove the disease classification performance via the given architecture than extant schemes.</p>\n </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"172 6","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Phytopathology","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jph.13388","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PLANT SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Plant diseases are the major factors that affects the quality production as it affects or interrupts the plant's vital functions. The early detection of crop disease could assist farmers in implementing the right preventative measures at the right moment to eradicate it. The main goal of the ODHEPDC (Optimal Trained Deep Hybrid Ensemble of Classifier for Classification of Plant Disease) model is the classification of diseases leaf images. The primary step is to improve the input image by using the MF model to remove the noise. This is considered as the preprocessing step. Improved fuzzy clustering algorithm, leading to the identification of the regions, ROI as well as non-ROI. Next to this, the appropriate features are extracted to define the feature set that includes MPPT feature, PHOG feature, and MTP features as well. However, the curse of dimensionality is the greatest crisis in the classification problem, hence, improved feature level fusion is progressed, which is the simple concatenation of the extracted features. In this, the improved calculation of information gain ensures the reduction and fusion of feature set. The fused features are the inputs to ensemble classification model with the classifiers like CNN, RNN, and DBN classifiers, which gives the classified results. To boost up the performance of classification model, the Deep Maxout model in the ensemble is optimally trained by a new Bald Eagle Search Updated Pelican Optimization (BESUPO) Algorithm via optimal weights tuning as the model determines the final classification outcome. The validation results prove the disease classification performance via the given architecture than extant schemes.
植物病害影响或中断植物的生命功能,是影响优质生产的主要因素。作物病害的早期发现可以帮助农民在适当的时候采取正确的预防措施来根除它。ODHEPDC (Optimal Trained Deep Hybrid Ensemble of Classifier for Classification of Plant Disease)模型的主要目标是对病害叶片图像进行分类。首先是利用MF模型对输入图像进行改进,去除噪声。这被认为是预处理步骤。改进模糊聚类算法,实现区域、感兴趣区域和非感兴趣区域的识别。接下来,提取适当的特性来定义包含MPPT特性、PHOG特性和MTP特性的特性集。然而,维数的缺失是分类问题中最大的危机,因此,提出了改进的特征级融合,即对提取的特征进行简单的拼接。其中,改进的信息增益计算保证了特征集的约简和融合。融合特征作为CNN、RNN、DBN等分类器集成分类模型的输入,给出分类结果。为了提高分类模型的性能,在模型确定最终分类结果时,采用一种新的白头鹰搜索更新鹈鹕优化(BESUPO)算法对集成中的Deep Maxout模型进行最优训练。验证结果表明,该体系结构的疾病分类性能优于现有方案。
期刊介绍:
Journal of Phytopathology publishes original and review articles on all scientific aspects of applied phytopathology in agricultural and horticultural crops. Preference is given to contributions improving our understanding of the biotic and abiotic determinants of plant diseases, including epidemics and damage potential, as a basis for innovative disease management, modelling and forecasting. This includes practical aspects and the development of methods for disease diagnosis as well as infection bioassays.
Studies at the population, organism, physiological, biochemical and molecular genetic level are welcome. The journal scope comprises the pathology and epidemiology of plant diseases caused by microbial pathogens, viruses and nematodes.
Accepted papers should advance our conceptual knowledge of plant diseases, rather than presenting descriptive or screening data unrelated to phytopathological mechanisms or functions. Results from unrepeated experimental conditions or data with no or inappropriate statistical processing will not be considered. Authors are encouraged to look at past issues to ensure adherence to the standards of the journal.