You are here

Asynchronous Distributed Clustering Algorithm for Wireless Sensor Networks

Authors: 
Publication Type: 
Refereed Conference Meeting Proceeding
Abstract: 
In distributed clustering problems, nodes in a wireless sensor network must learn clusters from the data sensed across the network, without centralising the raw data. This paper presents an asynchronous distributed clustering algorithm for sensors to learn the global clusters, while respecting data privacy, and balancing communication cost and clustering quality. Different clustering algorithms including k-means and Gaussian Mixture Models, and different methods of summarising clusters to exchange between nodes are considered. In experiments on randomly generated network topologies, we demonstrate that methods which do more extensive clustering in each cycle, and which exchange descriptions of cluster shape and density instead of just centroids and data counts, achieve more consistent clustering, in significantly shorter elapsed time.
Conference Name: 
4th Intl Conf on Machine Learning Technologies
Digital Object Identifer (DOI): 
10.1145/3340997.3341007
Publication Date: 
22/06/2019
Conference Location: 
China
Institution: 
National University of Ireland, Cork (UCC)
Open access repository: 
No
Publication document: