An Improved Clustering Scheme for Underwater Sensor Network using Bayesian Linear Regression
M Mathankumar, P. Thirumoorthi, Tamilarasu Viswanathan · 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) · 2021
Clustering scheme in Wireless Sensor Networks (WSN) is an optimum way for preserving energy of sensor nodes and achieving efficient data processing that maximizes the network lifetime. The concept of data enhancement clustering for better energy transfer in wireless sensor networks using Bayesian linear regression is presented in this work. The Underwater Sensor Network (USN) model with 100 nodes is uniformly distributed in random location within the search space. The basic linear regression coefficient analysis is presented for simple data clustering of proposed sensor node arrangement and Bayesian diffusion regression confirms the same level. The expansion of Bayesian diffusion of different distributions along with statistical parameters made individual node as better data clustering member. The degree of freedom of each node manages through better polynomial and avoiding the overfitted data of each node through ARIMA error included in regression and Quantile regression methods. The numerical validation reveals the superiority of the proposed schemes for better degree of freedom through statistical parameters.