Scholarlink

<p>Mobile Wireless Sensor Networks (MWSNs) are an emerging technology for next-generation healthcare, environmental monitoring, and industrial applications. Nevertheless, because of their ultra-small size, high mobility of nodes, and stringent energy limitations, efficient data transmission and network lifetime extension remain major challenges to date. To address these constraints, an integrated smart framework called Energy Efficient and Delay Sensitive Routing with Predictive Sink Mobility in Mobile Wireless Sensor Network using Triple Parallel Convolutional Neural Network Optimized by Cleaner Fish Algorithm (TPCNN-CFA) that integrates clustering, optimization, routing, and prediction is proposed. The data are gathered from fixed sensor nodes placed along a road that observe environmental parameters. To effectively manage these nodes, Anchor Graph-Based Multiview Fuzzy Clustering (AGMFC) is used. AGMFC takes into account various node features, such as position, energy, and data rate, for strong clustering. Then, the Artificial Protozoa Optimizer (APO) is used to find the best Cluster Head (CH) for optimal energy efficiency and load balancing throughout the network. Lastly, the Cleaner Fish Algorithm (CFA) is used to refine the Mobile Sink (MS) prediction process and scheduling tasks, and further improves the network performance and determines the optimal communication path. Thorough simulation results indicate that the proposed TPCNN-CFA framework greatly outperforms the current techniques in energy consumption, packet delivery, latency, and throughput with an overall accuracy of 99.8%, being highly efficient for energy-constrained mobility-aware MWSNs.</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

Energy efficient and delay sensitive routing with predictive sink mobility in mobile wireless sensor network using triple parallel convolutional neural network optimized by cleaner fish algorithm

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • Kuldeep Chouhan,
  • Kuthadi Venu Madhav,
  • Selvaraj Rajalakshmi,
  • N. Vinothkumar,
  • M. V. H. Bhaskara Murthy,
  • S. Balamuralitharan

摘要

Mobile Wireless Sensor Networks (MWSNs) are an emerging technology for next-generation healthcare, environmental monitoring, and industrial applications. Nevertheless, because of their ultra-small size, high mobility of nodes, and stringent energy limitations, efficient data transmission and network lifetime extension remain major challenges to date. To address these constraints, an integrated smart framework called Energy Efficient and Delay Sensitive Routing with Predictive Sink Mobility in Mobile Wireless Sensor Network using Triple Parallel Convolutional Neural Network Optimized by Cleaner Fish Algorithm (TPCNN-CFA) that integrates clustering, optimization, routing, and prediction is proposed. The data are gathered from fixed sensor nodes placed along a road that observe environmental parameters. To effectively manage these nodes, Anchor Graph-Based Multiview Fuzzy Clustering (AGMFC) is used. AGMFC takes into account various node features, such as position, energy, and data rate, for strong clustering. Then, the Artificial Protozoa Optimizer (APO) is used to find the best Cluster Head (CH) for optimal energy efficiency and load balancing throughout the network. Lastly, the Cleaner Fish Algorithm (CFA) is used to refine the Mobile Sink (MS) prediction process and scheduling tasks, and further improves the network performance and determines the optimal communication path. Thorough simulation results indicate that the proposed TPCNN-CFA framework greatly outperforms the current techniques in energy consumption, packet delivery, latency, and throughput with an overall accuracy of 99.8%, being highly efficient for energy-constrained mobility-aware MWSNs.