Adaptive Novelty Detection over Contextual Data Streams at the Edge using One-class Classification

Jodelka, O., Anagnostopoulos, C. and Kolomvatsos, K. (2021) Adaptive Novelty Detection over Contextual Data Streams at the Edge using One-class Classification. In: 12th International Conference on Information and Communication Systems (ICICS 2021), Valencia, Spain (Virtual), 24-26 May 2021, pp. 213-219. ISBN 9781665433518 (doi: 10.1109/ICICS52457.2021.9464585)

[img] Text
237685.pdf - Accepted Version



Online novelty detection is an emerging task in Edge Computing trying to identify novel concepts in contextual data streams which should be incorporated into predictive analytics and inferential models locally executed on edge computing nodes. We introduce an unsupervised adaptive mechanism for online novelty detection over multi-variate data streams at the network edge based on the One-class Support Vector Machine; an instance of One-class Classification paradigm. Due to the proposed adjustable periodic model retraining, our mechanism timely and effectively recognises novelties and resource-efficiently adapts to data streams. Our experimental evaluation and comparative assessment showcase the effectiveness and efficiency of the proposed mechanism over real data-streams in identifying novelty conditioned on the necessary model retraining epochs.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Anagnostopoulos, Dr Christos and Kolomvatsos, Dr Kostas
Authors: Jodelka, O., Anagnostopoulos, C., and Kolomvatsos, K.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2021 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher
Related URLs:

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