Adaptive principal component analysis-based outliers detection through neighbourhood voting in wireless sensor networks

Aleksandrova, E. and Anagnostopoulos, C. (2019) Adaptive principal component analysis-based outliers detection through neighbourhood voting in wireless sensor networks. In: Comşa, I.-S. and Trestian, R. (eds.) Next-Generation Wireless Networks Meet Advanced Machine Learning Applications. IGI Global, pp. 255-285. ISBN 9781522574583 (doi: 10.4018/978-1-5225-7458-3.ch011)

Abstract

This chapter introduces statistical learning methods and findings of a group decision-making algorithm in Internet of Things (IoT) and Edge Computing environments. The discussed methodology locally detects outliers in an on-line and adaptive mode. It is driven by three perspectives: opinion, confidence and independence; and exploits the incremental Principal Component Analysis using the Power Method for eigenvector and eigenvalue estimation and Knuth and Welford’s online algorithms for variance estimation. The methodology is implemented and evaluated over real contextual data in a wireless network of environmental sensors from where appropriate conclusions are drawn about the capabilities and limitations of the proposed solution in IoT environments.

• Item Type: Book Sections
• Status: Published
• Glasgow Author(s) Enlighten ID: Anagnostopoulos, Dr Christos and Aleksandrova, Ms Ekaterina
• Authors: Aleksandrova, E., and Anagnostopoulos, C.
• College/School: College of Science and Engineering > School of Computing Science
• Publisher: IGI Global
• ISBN: 9781522574583