A one-class clustering technique for novelty detection and Isolation in sensor networks

Maleki, Sepehr and Bingham, Chris (2017) A one-class clustering technique for novelty detection and Isolation in sensor networks. In: IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, 26 - 28 June 2017, Annecy, France.

Documents
07995292.pdf
[img] PDF
07995292.pdf - Whole Document
Restricted to Repository staff only

1MB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

A new Cluster-based methodology for real-time Novelty Detection and Isolation (NDI) in sensor networks, is presented. The proposed algorithm enables uniform clustering across time-frames to indicate the presence of a “healthy” network. In the event of novelty, the associated sensor is seen to be clustered in a non-uniform manner with respect other sensors in the network, thereby facilitating fault isolation. Moreover, a statistical approach is proposed to determine a noise tolerance level for reducing false alarms. Performance of the proposed algorithm is examined using datasets obtained from a number of industrial case studies, and the significance for fault detection for such systems is demonstrated. Specifically, it is shown that through a correct selection of the noise tolerance level, an emerging failure is successfully isolated in presence of other abrupt changes that visually might be perceived as indication of a failure.

Keywords:Clustering analysis, automated classification, Wireless Sensor Networks (WSNs)
Subjects:H Engineering > H130 Computer-Aided Engineering
H Engineering > H321 Turbine Technology
Divisions:College of Science > School of Engineering
Related URLs:
ID Code:31513
Deposited On:04 Apr 2018 10:18

Repository Staff Only: item control page