Scholarlink

<p>This paper presents a systematic review of methodologies for plant disease detection, structured using the PRISMA model to ensure a systematic and reliable research approach. The study examines 108 research papers from reputable databases, highlighting cutting-edge techniques. It includes a detailed dataset glossary, preprocessing, and explanations of the datasets used, providing essential context about data sources and samples. Additionally, a glossary of plant diseases offers a deeper understanding of the scope of detected diseases. This review highlights the importance of machine learning (ML) and deep learning (DL) approaches, such as the support vector machine (SVM), random forest, decision tree, convolutional neural networks (CNN), transfer learning techniques, and long short-term memory (LSTM) approaches, in improving plant disease identification. It also presents a structured overview of metaheuristic optimization methods, including Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO), which are used to boost model performance. Performance evaluation parameters critical for assessing model efficacy are also discussed. This review is a valuable resource for researchers, contributing significantly to advancements in detecting agricultural plant disease.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Cutting-edge approaches to plant disease detection: a survey of machine learning models and optimization methods

  • 期刊论文

  • 发表日期：

    2025年8月13日

查看全文
  • Shantilata Palei,
  • Puspanjali Mohapatra

摘要

This paper presents a systematic review of methodologies for plant disease detection, structured using the PRISMA model to ensure a systematic and reliable research approach. The study examines 108 research papers from reputable databases, highlighting cutting-edge techniques. It includes a detailed dataset glossary, preprocessing, and explanations of the datasets used, providing essential context about data sources and samples. Additionally, a glossary of plant diseases offers a deeper understanding of the scope of detected diseases. This review highlights the importance of machine learning (ML) and deep learning (DL) approaches, such as the support vector machine (SVM), random forest, decision tree, convolutional neural networks (CNN), transfer learning techniques, and long short-term memory (LSTM) approaches, in improving plant disease identification. It also presents a structured overview of metaheuristic optimization methods, including Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO), which are used to boost model performance. Performance evaluation parameters critical for assessing model efficacy are also discussed. This review is a valuable resource for researchers, contributing significantly to advancements in detecting agricultural plant disease.