Author ORCID Identifier

https://orcid.org/0000-0001-6462-3248

Document Type

Article

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Publication Details

Knowledge-Based Systems, Volume 257, 5 December 2022, 109894

Open access

https://www.sciencedirect.com/science/article/pii/S095070512200987X#d1e1490

Abstract

This paper examines how data normalisation and clustering interact in the definition of sub-domains within multi-source transfer learning systems for time series anomaly detection. The paper introduces a distinction between (i) clustering as a primary/direct method for anomaly detection, and (ii) clustering as a method for identifying sub-domains within the source or target datasets. Reporting the results of three sets of experiments, we find that normalisation after feature extraction and before clustering results in the best performance for anomaly detection. Interestingly, we find that in the multi-source transfer learning scenario clustering on the target dataset and identifying subdomains in the target data can result in improved model performance, as compared to identifying sub-domains through defining clusters using the multi-source dataset.

DOI

https://doi.org/10.1016/j.knosys.2022.109894

Funder

SFI ADAPT Centre

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


Share

COinS