Scholarlink

<p>Banana is a vital worldwide crop that sustains food security and economic welfare. Banana leaf spot (BLS) is the most damaging fungus affecting banana production because it is caused by <i>Mycosphaerella fijiensis</i>. Detecting banana leaf spot early remains crucial because the disease causes significant production losses and affects the quality of fruits. Disease detection through visual examination proves inefficient because it requires lengthy manual assessment periods. We created a cutting-edge solution for early BLS discovery by combining IoT technology with NPK (nitrogen, phosphorus, potassium) soil correlation analysis. The proposed system utilizes an IoT board with precise sensors that determine current NPK soil measurements during operation. The microcontroller receives data from sensors that connect to it to transmit it through a cloud server for analysis. The system depends on machine learning to identify soil abnormalities while creating a link between NPK changes and BLS disease occurrences. By integrating support vector machine (SVM) models with Newton's optimization algorithm, the system achieves higher accuracy rates for detecting BLS infection through significant deviation indicators. Due to its small size, the cost-effective IoT-based system enables simple installation, which supports uninterrupted soil checks within banana plantations. An internet platform enables farmers and agricultural experts to check real-time soil data, generating immediate alerts regarding BLS outbreaks. Multinational potato farmers now take preventive measures that allow them to detect BLS infections earlier, thus reducing damage to their crops. An efficient, scalable, innovative solution emerges through IoT technology, soil nutrient analysis and machine learning for banana disease control. Staff monitoring soil conditions through remote systems acquire data for better crop decisions that improve banana sustainability and productivity.</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

To Design and Develop the IoT Board to Retrieve NPK Data and Predict the Banana Leaf Diseases(BLS) Using SVM with Newtons Optimization Algorithm

  • 期刊论文

  • 发表日期：

    2025年5月14日

查看全文
  • Ravi Kumar Tirandasu,
  • Prasanth Yalla

摘要

Banana is a vital worldwide crop that sustains food security and economic welfare. Banana leaf spot (BLS) is the most damaging fungus affecting banana production because it is caused by Mycosphaerella fijiensis. Detecting banana leaf spot early remains crucial because the disease causes significant production losses and affects the quality of fruits. Disease detection through visual examination proves inefficient because it requires lengthy manual assessment periods. We created a cutting-edge solution for early BLS discovery by combining IoT technology with NPK (nitrogen, phosphorus, potassium) soil correlation analysis. The proposed system utilizes an IoT board with precise sensors that determine current NPK soil measurements during operation. The microcontroller receives data from sensors that connect to it to transmit it through a cloud server for analysis. The system depends on machine learning to identify soil abnormalities while creating a link between NPK changes and BLS disease occurrences. By integrating support vector machine (SVM) models with Newton's optimization algorithm, the system achieves higher accuracy rates for detecting BLS infection through significant deviation indicators. Due to its small size, the cost-effective IoT-based system enables simple installation, which supports uninterrupted soil checks within banana plantations. An internet platform enables farmers and agricultural experts to check real-time soil data, generating immediate alerts regarding BLS outbreaks. Multinational potato farmers now take preventive measures that allow them to detect BLS infections earlier, thus reducing damage to their crops. An efficient, scalable, innovative solution emerges through IoT technology, soil nutrient analysis and machine learning for banana disease control. Staff monitoring soil conditions through remote systems acquire data for better crop decisions that improve banana sustainability and productivity.