Scholarlink

<p>Accurate positioning is essential for effective monitoring localization is vital in wireless sensor networks (WSNs), especially in dynamic and resource-constrained environments. This work presents a fuzzy clustering-based localization method that integrates an improved sampling box with a multidimensional Gaussian model and time series–optimized fuzzy reasoning. The approach balances accuracy, interpretability, and efficiency by adaptively refining membership degrees and handling asynchronous updates. Experiments on UCI and MIT Reality datasets demonstrate a stable Rand Index of 0.89 and an average positioning error of 0.21&#xa0;m with 40% beacon nodes. The model also achieves the fastest response times among comparative methods, demonstrating strong scalability and efficiency. It further ensures fast response and scalability with larger networks, while remaining robust under dynamic topologies. This method offers a robust solution for high-precision localization in applications such as Validated on UCI and MIT Reality datasets; the method supports practical applications in environmental monitoring and industrial automation.</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

Enhanced Localization in Wireless Sensor Networks Using Optimized Sampling and Fuzzy Logic

  • 期刊论文

  • 发表日期：

    2026年3月4日

查看全文
  • Cuiying Lu

摘要

Accurate positioning is essential for effective monitoring localization is vital in wireless sensor networks (WSNs), especially in dynamic and resource-constrained environments. This work presents a fuzzy clustering-based localization method that integrates an improved sampling box with a multidimensional Gaussian model and time series–optimized fuzzy reasoning. The approach balances accuracy, interpretability, and efficiency by adaptively refining membership degrees and handling asynchronous updates. Experiments on UCI and MIT Reality datasets demonstrate a stable Rand Index of 0.89 and an average positioning error of 0.21 m with 40% beacon nodes. The model also achieves the fastest response times among comparative methods, demonstrating strong scalability and efficiency. It further ensures fast response and scalability with larger networks, while remaining robust under dynamic topologies. This method offers a robust solution for high-precision localization in applications such as Validated on UCI and MIT Reality datasets; the method supports practical applications in environmental monitoring and industrial automation.