TY - GEN
T1 - Location Based Distributed Spectral Clustering for Wireless Sensor Networks
AU - Muniraju, Gowtham
AU - Zhang, Sai
AU - Tepedelenlioglu, Cihan
AU - Banavar, Mahesh K.
AU - Spanias, Andreas
AU - Vargas-Rosales, Cesar
AU - Villalpando-Hernandez, Rafaela
N1 - Funding Information:
The authors from Arizona State University are funded in part by the NSF award ECSS 1307982, NSF CPS award 1646542 and the SenSIP Center, School of ECEE, Arizona State University.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/20
Y1 - 2017/12/20
N2 - A distributed spectral clustering algorithm to group sensors based on their location in a wireless sensor network (WSN) is proposed. For machine learning and data mining applications in WSN's, gathering data at a fusion center is vulnerable to attacks and creates data congestion. To avoid this, we propose a robust distributed clustering method without a fusion center. The algorithm combines distributed eigenvector computation and distributed K-means clustering. A distributed power iteration method is used to compute the eigenvector of the graph Laplacian. At steady state, all nodes converge to a value in the eigenvector of the algebraic connectivity of the graph Laplacian. Clustering is carried out on the eigenvector using a distributed K-means algorithm. Location information of the sensor is only used to establish the network topology and this information is not exchanged in the network. This algorithm works for any connected graph structure. Simulation results supporting the theory are also provided.
AB - A distributed spectral clustering algorithm to group sensors based on their location in a wireless sensor network (WSN) is proposed. For machine learning and data mining applications in WSN's, gathering data at a fusion center is vulnerable to attacks and creates data congestion. To avoid this, we propose a robust distributed clustering method without a fusion center. The algorithm combines distributed eigenvector computation and distributed K-means clustering. A distributed power iteration method is used to compute the eigenvector of the graph Laplacian. At steady state, all nodes converge to a value in the eigenvector of the algebraic connectivity of the graph Laplacian. Clustering is carried out on the eigenvector using a distributed K-means algorithm. Location information of the sensor is only used to establish the network topology and this information is not exchanged in the network. This algorithm works for any connected graph structure. Simulation results supporting the theory are also provided.
KW - Wireless sensor network
KW - consensus
KW - distributed K-means
KW - machine learning
KW - spectral clustering
UR - http://www.scopus.com/inward/record.url?scp=85047464511&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047464511&partnerID=8YFLogxK
U2 - 10.1109/SSPD.2017.8233241
DO - 10.1109/SSPD.2017.8233241
M3 - Conference contribution
AN - SCOPUS:85047464511
T3 - 2017 Sensor Signal Processing for Defence Conference, SSPD 2017
SP - 1
EP - 5
BT - 2017 Sensor Signal Processing for Defence Conference, SSPD 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th Conference of the Sensor Signal Processing for Defence, SSPD 2017
Y2 - 6 December 2017 through 7 December 2017
ER -