Performance evaluation of real-time multivariate data reduction models for adaptive-threshold in wireless sensor networks

Alduais, N.A.M., Abdullah, J., Jamil, A. and Heidari, H. (2017) Performance evaluation of real-time multivariate data reduction models for adaptive-threshold in wireless sensor networks. IEEE Sensors Letters, 1(6), 7501204. (doi: 10.1109/LSENS.2017.2768218)

[img]
Preview
Text
150648.pdf - Accepted Version

493kB

Abstract

This paper presents a new metric to assess the performance of different multivariate data reduction models in wireless sensor networks (WSNs). The proposed metric is called Updating Frequency Metric (UFM) which is defined as the frequency of updating the model reference parameters during data collection. A method for estimating the error threshold value during the training phase is also suggested. The proposed threshold of error is used to update the model reference parameters when it is necessary. Numerical analysis and simulation results show that the proposed metric validates its effectiveness in the performance of multivariate data reduction models in terms of the sensor node energy consumption. Furthermore, the proposed adaptive threshold enhances the model's performance more than the non-adaptive threshold in decreasing the frequency of updating the model reference parameters which positively prolongs the lifetime of the node. The adaptive threshold improves the frequency of updating the parameters by 80% and 52% in comparison to the non-adaptive threshold for multivariate data reduction models of MLR-B and PCA-B respectively.

Item Type:Articles
Additional Information:This research is supported by the Fundamental Research Grant Scheme (FRGS) vote number 1532 from the Ministry of Education Malaysia.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Heidari, Professor Hadi
Authors: Alduais, N.A.M., Abdullah, J., Jamil, A., and Heidari, H.
College/School:College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
Journal Name:IEEE Sensors Letters
Journal Abbr.:SENSL
Publisher:IEEE
ISSN:2475-1472
Published Online:02 November 2017
Copyright Holders:Copyright © 2017 IEEE
First Published:First published in IEEE Sensors Letters 1(6):7501204
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher

University Staff: Request a correction | Enlighten Editors: Update this record