Scholarlink

Wireless Sensor Networks (WSNs) consists of number of wireless sensor nodes located around the geographical locations. In the deployment of WSN, there is required to know the senor deployment details in prior. The large number of data captured through the Sensor Node (SN) utilizes the SN’s minimum energy as well as confuse the data analysis at Base Station or sink for the decision making. The essential accurate evaluation of the parameters such as distance among the nodes, network lifetime, utilization of number of nodes as well as communication channel parameters. In this research, the Machine Learning (ML) algorithms of ensemble Artificial Neural Network (ANN) and Support Vector Machine (SVM) is proposed for speed up the parameters evaluations with efficient accurate results. The performance of the proposed ANN-SVM method attains better results and it achieves the network lifetime of 8345, prediction error of 0.09, Mean Square Error (MSE) of 0.005637, Mean Absolute Error (MAE) of 0.064571 and Root Mean Square Error (RMSE) of 0.07356 when compared to the existing methods such as Support Vector Regression (SVR) and Deep Neural Network.

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

Ensemble Artificial Neural Network and Support Vector Machine Based Parameter Evaluation in Wireless Sensor Networks

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mohammed Ayad Alkhafaji,
  • Nagendar Yamsani,
  • P. Rashmi,
  • N. V. Babu

摘要

Wireless Sensor Networks (WSNs) consists of number of wireless sensor nodes located around the geographical locations. In the deployment of WSN, there is required to know the senor deployment details in prior. The large number of data captured through the Sensor Node (SN) utilizes the SN’s minimum energy as well as confuse the data analysis at Base Station or sink for the decision making. The essential accurate evaluation of the parameters such as distance among the nodes, network lifetime, utilization of number of nodes as well as communication channel parameters. In this research, the Machine Learning (ML) algorithms of ensemble Artificial Neural Network (ANN) and Support Vector Machine (SVM) is proposed for speed up the parameters evaluations with efficient accurate results. The performance of the proposed ANN-SVM method attains better results and it achieves the network lifetime of 8345, prediction error of 0.09, Mean Square Error (MSE) of 0.005637, Mean Absolute Error (MAE) of 0.064571 and Root Mean Square Error (RMSE) of 0.07356 when compared to the existing methods such as Support Vector Regression (SVR) and Deep Neural Network.