Welcome to the InfoSci Platform
Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony

Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony

Osman Salem, Yaning Liu, Ahmed Mehaoua
Copyright: © 2014 |Volume: 5 |Issue: 4 |Pages: 19
ISSN: 1947-315X|EISSN: 1947-3168|EISBN13: 9781466654020|DOI: 10.4018/ijehmc.2014100102
Cite Article Cite Article

MLA

Salem, Osman, et al. "Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony." IJEHMC vol.5, no.4 2014: pp.20-38. http://doi.org/10.4018/ijehmc.2014100102

APA

Salem, O., Liu, Y., & Mehaoua, A. (2014). Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony. International Journal of E-Health and Medical Communications (IJEHMC), 5(4), 20-38. http://doi.org/10.4018/ijehmc.2014100102

Chicago

Salem, Osman, Yaning Liu, and Ahmed Mehaoua. "Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony," International Journal of E-Health and Medical Communications (IJEHMC) 5, no.4: 20-38. http://doi.org/10.4018/ijehmc.2014100102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Wireless sensor networks are subject to different types of faults and interferences after their deployment. Abnormal values reported by sensors should be separated from faulty or injected measurements to ensure reliable monitoring operation. The aim of this paper is to propose a lightweight approach for the detection and suppression of faulty measurements in medical wireless sensor networks. The proposed approach is based on the combination of statistical model and machine learning algorithm. The authors begin by collecting physiological data and then they cluster the data collected during the first few minutes using the Gaussian mixture decomposition. They use the resulted labeled data as the input for the Ant Colony algorithm to derive classification rules in the central base station. Afterward, the derived rules are transmitted and installed in each associated sensor to detect abnormal values in distributed manner, and notify anomalies to the base station. Finally, the authors exploit the spatial and temporal correlations between monitored attributes to differentiate between faulty sensor readings and clinical emergency. They evaluate their approach with real and synthetic patient datasets. The experimental results demonstrate that their proposed approach achieves a high rate of detection accuracy for clinical emergency with reduced false alarm rate when compared to robust Mahalanobis distance.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.