Scholarlink

<p>As the world population and food demand grow, intelligent agriculture will become even more important. Internet of Things (IoT) technologies provide creative agricultural solutions in this area. But IoT nodes frequently encounter energy limitations and intricate routing problems, which can result in delays in IoT-based agriculture, high energy consumption, data transmission errors, and shortened network lifetimes. Using an optimized Siamese graph convolutional attention network (EEC-OSGCAN) based on energy-efficient clustering, this study suggested a fresh solution to these problems: intelligent smart agricultural production systems. This system uses the Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering Algorithm with Running City Game Optimizer, a novel technique for creating and choosing the best cluster heads, to improve energy management performance. In addition to reducing energy usage and increasing network lifetime, these clusters make it easier to gather and interpret agricultural data. Additionally, to evaluate the gathered agricultural data and derive insightful information, deep learning techniques like the Siamese graph convolutional attention network (SGCAN) algorithm, optimized with Crested Porcupine Optimizer (SGCAN-CPO), are used. They anticipate crop health, soil moisture content, and other important aspects accurately, which enables farmers to make better decisions and use resources as efficiently as possible. To do the experimental simulations, the Python platform is used. The findings demonstrate that the new strategy outperforms earlier methods in several performance metrics, including higher throughput (98%), higher packet delivery ratio (0.993%), and lower energy consumption (0.40&#xa0;mJ). This shows how effective the method is and how much room there is for advancement in the field.</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

Intelligent smart agricultural production systems with energy efficient clustering-based optimized Siamese graph convolutional attention network

  • 期刊论文

  • 发表日期：

    2025年10月9日

查看全文
  • K. Muruganandam,
  • Usha Chauhan

摘要

As the world population and food demand grow, intelligent agriculture will become even more important. Internet of Things (IoT) technologies provide creative agricultural solutions in this area. But IoT nodes frequently encounter energy limitations and intricate routing problems, which can result in delays in IoT-based agriculture, high energy consumption, data transmission errors, and shortened network lifetimes. Using an optimized Siamese graph convolutional attention network (EEC-OSGCAN) based on energy-efficient clustering, this study suggested a fresh solution to these problems: intelligent smart agricultural production systems. This system uses the Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering Algorithm with Running City Game Optimizer, a novel technique for creating and choosing the best cluster heads, to improve energy management performance. In addition to reducing energy usage and increasing network lifetime, these clusters make it easier to gather and interpret agricultural data. Additionally, to evaluate the gathered agricultural data and derive insightful information, deep learning techniques like the Siamese graph convolutional attention network (SGCAN) algorithm, optimized with Crested Porcupine Optimizer (SGCAN-CPO), are used. They anticipate crop health, soil moisture content, and other important aspects accurately, which enables farmers to make better decisions and use resources as efficiently as possible. To do the experimental simulations, the Python platform is used. The findings demonstrate that the new strategy outperforms earlier methods in several performance metrics, including higher throughput (98%), higher packet delivery ratio (0.993%), and lower energy consumption (0.40 mJ). This shows how effective the method is and how much room there is for advancement in the field.