Concept Drift Detection with Clustering via Statistical Change Detection Methods

We propose a concept drift detection method utilizing statistical change detection in which a drift detection method and the Page-Hinkley test are employed. Our method enables users to annotate clustering results without constructing a model of drift detection for every input. In our experiments using synthetic data, we evaluated our proposed method on the basis of detection delay and false detection, also revealed relations between the degree of drift and parameters of the method.

[1]  Žliobait . e,et al.  Learning under Concept Drift: an Overview , 2010 .

[2]  Younès Bennani,et al.  Change detection in data streams through unsupervised learning , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[3]  João Gama,et al.  Learning with Drift Detection , 2004, SBIA.

[4]  A. Bifet,et al.  Early Drift Detection Method , 2005 .

[5]  Koichiro Yamauchi,et al.  Detecting Concept Drift Using Statistical Testing , 2007, Discovery Science.

[6]  David V. Hinkley,et al.  Inference about the change-point in a sequence of binomial variables , 1970 .

[7]  Masayuki Numao,et al.  Visualization of Damage Progress in Solid Oxide Fuel Cells , 2011 .

[8]  Indre Zliobaite,et al.  Learning under Concept Drift: an Overview , 2010, ArXiv.

[9]  Dimitris K. Tasoulis,et al.  Exponentially weighted moving average charts for detecting concept drift , 2012, Pattern Recognit. Lett..

[10]  Hans-Jürgen Appelrath,et al.  Data Stream Management in the AAL: Universal and Flexible Preprocessing of Continuous Sensor Data , 2012 .

[11]  S. Panchapakesan,et al.  Inference about the Change-Point in a Sequence of Random Variables: A Selection Approach , 1988 .

[12]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[13]  Timo Michelsen,et al.  Odysseus: a highly customizable framework for creating efficient event stream management systems , 2012, DEBS.

[14]  Shai Ben-David,et al.  Detecting Change in Data Streams , 2004, VLDB.

[15]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Data stream clustering: A survey , 2013, CSUR.

[16]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Unsupervised density-based behavior change detection in data streams , 2014, Intell. Data Anal..

[17]  H. Mouss,et al.  Test of Page-Hinckley, an approach for fault detection in an agro-alimentary production system , 2004, 2004 5th Asian Control Conference (IEEE Cat. No.04EX904).