RT info:eu-repo/semantics/article
T1 Combining univariate approaches for ensemble change detection in multivariate data
A1 Faithfull, William J. .
A1 Rodríguez Diez, Juan José
A1 Kuncheva, Ludmila I. .
K1 Computer science
K1 Informática
AB 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.
PB Elsevier
SN 1566-2535
YR 2019
FD 2019-01
LK http://hdl.handle.net/10259/4749
UL http://hdl.handle.net/10259/4749
LA eng
NO project RPG-2015-188 funded by TheLeverhulme Trust, UK; Spanish Ministry of Economy andCompetitiveness through project TIN 2015-67534-P and the SpanishMinistry of Education, Culture and Sport through Mobility GrantPRX16/00495. The 96 datasets were originally curated for use in thework of Fernández-Delgado et al. [53] and accessed from the personalweb page of the author5. The KDD Cup 1999 dataset used in the casestudy was accessed from the UCI Machine Learning Repository [10]
DS Repositorio Institucional de la Universidad de Burgos
RD 24-abr-2024