Scholarlink

<p>Cattle farming environments pose unique challenges for wireless sensor networks (WSNs) due to their dynamic nature and large-scale spatial requirements. Existing localization methods often struggle to achieve accurate positioning of sensor nodes, leading to inefficiencies in disease monitoring and management. In this paper, we propose an Integrated Optimization and Disease Management System for Cattle Farming Environments (IODM-CF) that addresses these challenges. Our framework integrates two key components: the Modified Seagull Optimization Algorithm (MSOA) for anchor node localization and Exploration-Enhanced Multi-Agent Q Learning (EE-MAQ) for proactive disease forecasting. The MSOA strategically places anchor nodes while considering coverage requirements, cost constraints, and dynamic environmental changes. Adaptive exploration and real-time recalibration mechanisms optimize localization accuracy and energy efficiency. Additionally, our system utilizes EE-MAQ for disease prediction, leveraging localization data for precise forecasting and timely management actions. Evaluation results demonstrate the superiority of IODM-CF over existing methods, with mean localization errors reduced to 4.23% and 4.89% for anchor and sensor nodes, respectively. Additionally, disease prediction accuracy reaches 98.0%, outperforming existing methods. IODM-CF offers a robust solution for accurate localization and proactive disease management in cattle farming environments, with significant improvements in performance metrics.</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

An integrated localization and proactive disease forecasting system for cattle farming environments in wireless sensor networks

  • 期刊论文

  • 发表日期：

    2025年1月24日

查看全文
  • S. Benjamin Arul,
  • G. D. Anbarasi Jebaselvi

摘要

Cattle farming environments pose unique challenges for wireless sensor networks (WSNs) due to their dynamic nature and large-scale spatial requirements. Existing localization methods often struggle to achieve accurate positioning of sensor nodes, leading to inefficiencies in disease monitoring and management. In this paper, we propose an Integrated Optimization and Disease Management System for Cattle Farming Environments (IODM-CF) that addresses these challenges. Our framework integrates two key components: the Modified Seagull Optimization Algorithm (MSOA) for anchor node localization and Exploration-Enhanced Multi-Agent Q Learning (EE-MAQ) for proactive disease forecasting. The MSOA strategically places anchor nodes while considering coverage requirements, cost constraints, and dynamic environmental changes. Adaptive exploration and real-time recalibration mechanisms optimize localization accuracy and energy efficiency. Additionally, our system utilizes EE-MAQ for disease prediction, leveraging localization data for precise forecasting and timely management actions. Evaluation results demonstrate the superiority of IODM-CF over existing methods, with mean localization errors reduced to 4.23% and 4.89% for anchor and sensor nodes, respectively. Additionally, disease prediction accuracy reaches 98.0%, outperforming existing methods. IODM-CF offers a robust solution for accurate localization and proactive disease management in cattle farming environments, with significant improvements in performance metrics.