Title: Data stream mining for wireless sensor networks environment: energy efficient fuzzy clustering algorithm

Authors: Hakilo Sabit; Adnan Al-Anbuky; Hamid Gholamhosseini

Addresses: Sensor Network and Smart Environment, Research Centre (SeNSe), Auckland University of Technology (AUT), Private Bag 92006, Auckland 1142, New Zealand ' Sensor Network and Smart Environment, Research Centre (SeNSe), Auckland University of Technology (AUT), Private Bag 92006, Auckland 1142, New Zealand ' Department of Electrical and Electronic Engineering, Auckland University of Technology (AUT), Private Bag 92006, Auckland 1142, New Zealand

Abstract: This paper proposes a distributed wireless sensor network data stream clustering algorithm to minimise energy consumption and consequently extend the network lifetime. The efficiency in energy usage is as a result of trading-off communication for computation through distributed clustering and successive transmission of local clusters. We present the development of our algorithm, subtractive fuzzy cluster means (SUBFCM), and analyse its energy efficiency as well as clustering performance in comparison with state-of-the-art standard data clustering algorithms such as fuzzy C-means and K-means algorithms. The significance of the SUBFCM algorithm in terms of energy efficiency and clustering performance is proved through simulations as well as experiments.

Keywords: wireless sensor networks; WSNs; WSN data stream mining; energy efficient clustering; fuzzy clustering; clustering algorithms; adaptive data stream mining; distributed data stream mining; energy consumption; network lifetime.

DOI: 10.1504/IJAACS.2011.043478

International Journal of Autonomous and Adaptive Communications Systems, 2011 Vol.4 No.4, pp.383 - 397

Published online: 24 Jan 2015 *

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