Title: Entropy correlation-based clustering method for representative data aggregation in wireless sensor networks

Authors: Nguyen Thi Thanh Nga; Nguyen Kim Khanh; Ngo Hong Son

Addresses: School of Information and Communication Technology, Hanoi University of Science and Technology, No. 1, Dai Co Viet Street, Hanoi, 11615, Vietnam ' School of Information and Communication Technology, Hanoi University of Science and Technology, No. 1, Dai Co Viet Street, Hanoi, 11615, Vietnam ' School of Information and Communication Technology, Hanoi University of Science and Technology, No. 1, Dai Co Viet Street, Hanoi, 11615, Vietnam

Abstract: One of the popular data aggregation method in wireless sensor network (WSN) is collecting only local representative data based on correlation of sample data. To recognise the local representative nodes, it is necessary to determine the correlation regions. However, recent correlation models are distance based that is not general and need to be determined beforehand or complicated with high computing cost. Thus, in this paper, a novel entropy correlation model is proposed based on joint entropy approximation. Using the proposed model, an entropy correlation-based clustering method is presented and the selection of representative data that satisfying the desired distortion is proposed. The algorithm is validated with practical data.

Keywords: WSN; wireless sensor network; correlation; entropy; clustering; representative nodes.

DOI: 10.1504/IJSNET.2018.096476

International Journal of Sensor Networks, 2018 Vol.28 No.4, pp.270 - 283

Received: 10 Oct 2017
Accepted: 03 May 2018

Published online: 29 Nov 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article