An efficient scheme of target classification and information fusion in wireless sensor networks

Authors:
Youngsoo Kim;Sangbae Jeong;Daeyoung Kim;Tomás Sánchez López
Affiliations:
Real-time and Embedded System Laboratory, Information and Communications University, Daejon, Korea 305-732;Electronics Engineering Department, Gyeongsang National University, Jinju, Korea 660-701;Real-time and Embedded System Laboratory, Information and Communications University, Daejon, Korea 305-732;Real-time and Embedded System Laboratory, Information and Communications University, Daejon, Korea 305-732
Venue:
Personal and Ubiquitous Computing
Year:
2009

Citing 6
Cited 4

Fundamentals of statistical signal processing: estimation theory

Fundamentals of statistical signal processing: estimation theory
Comparison of different implementations of MFCC

Journal of Computer Science and Technology
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Vehicle classification in distributed sensor networks

Journal of Parallel and Distributed Computing
A line in the sand: a wireless sensor network for target detection, classification, and tracking

Computer Networks: The International Journal of Computer and Telecommunications Networking - Special issue: Military communications systems and technologies

Fast, accurate event classification on resource-lean embedded sensors

EWSN'11 Proceedings of the 8th European conference on Wireless sensor networks
Fast, Accurate Event Classification on Resource-Lean Embedded Sensors

ACM Transactions on Autonomous and Adaptive Systems (TAAS)
An algorithm on fairness verification of mobile sink routing in wireless sensor network

Personal and Ubiquitous Computing
Towards augmenting federated wireless sensor networks in forestry applications

Personal and Ubiquitous Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an efficient target classification and fusion scheme for wireless sensor networks (WSNs) is proposed and evaluated. When a classification algorithm for WSN nodes is designed, parametric approaches such as Gaussian mixture model (GMM) should be more preferred to non-parametric ones due to the hard limitation in resources. The GMM algorithm not only shows good performances for target classification in WSNs but it also requires very small resources. Based on the classifier, a decision tree generated by the classification and regression tree algorithm is used to fuse the information from heterogeneous sensors. This node-level classification scheme provides a satisfactory classification rate, 94.10%, with little resources. Finally, a confidence-based fusion algorithm improves the overall accuracy by fusing the information among sensor nodes. Our experimental results show that the proposed group-level fusion algorithm improves the accuracy by an average of 4.17% accuracy with randomly selected nodes.