2024-03-29T15:56:38Zhttps://riubu.ubu.es/oai/requestoai:riubu.ubu.es:10259/47492022-04-29T12:02:45Zcom_10259_4219com_10259_5086com_10259_2604col_10259_4220
Combining univariate approaches for ensemble change detection in multivariate data
Faithfull, William J. .
Rodríguez Diez, Juan José
Kuncheva, Ludmila I. .
Detecting change in multivariate data is a challenging problem, especially when class labels are not available. There is a large body of research on univariate change detection, notably in control charts developed originally for engineering applications. We evaluate univariate change detection approaches —including those in the MOA framework — built into ensembles where each member observes a feature in the input space of an unsupervised change detection problem. We present a comparison between the ensemble combinations and three established ‘pure’ multivariate approaches over 96 data sets, and a case study on the KDD Cup 1999 network intrusion detection dataset. We found that ensemble combination of univariate methods consistently outperformed multivariate methods on the four experimental metrics.
2018-03-09
2019-01
2021-01
info:eu-repo/semantics/article
1566-2535
http://hdl.handle.net/10259/4749
10.1016/j.inffus.2018.02.003
eng
Information Fusion. 2019, V. 45, p. 202-214
https://doi.org/10.1016/j.inffus.2018.02.003
info:eu-repo/grantAgreement/Leverhulme Trust/RPG-2015-188
info:eu-repo/grantAgreement/MINECO/TIN 2015-67534-P
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
Attribution-NonCommercial-NoDerivatives 4.0 International
Elsevier