TY - CPAPER TI - Concept Drift Detection with Clustering via Statistical Change Detection Methods AU - Nicklas, Daniela AU - Fukui, Ken-Ichi AU - Gama, João AU - Moriyama, Koichi AU - Numao, Masayuki AU - Sakamoto, Yusuke PY - 2015 T2 - Proceedings: 2015 Seventh International Conference on Knowledge and Systems Engineering (KSE) SP - 37-42 PB - IEEE CY - New York, NY, USA DO - 10.1109/KSE.2015.19 UR - https://fis.uni-bamberg.de/handle/uniba/44519 LA - eng AB - 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. ER -