clustering-inverse a generalized model for pattern-based time series segmentationclustering-inverse基于模式的广义模型时间序列分割.pdfVIP

Journal of Intelligent Learning Systems and Applications, 2011, 3, 26-36 doi:10.4236/jilsa.2011.31004 Published Online February 2011 (http://www.SciRP.org/journal/jilsa) Clustering-Inverse: A Generalized Model for Pattern-Based Time Series Segmentation* 1,2 2 1,2 Zhaohong Deng , Fu-Lai Chung , Shitong Wang 1School of Information, Jiangnan University, Wuxi, China; 2Department of Computing, Hong Kong Polytechnic University, Hong Kong, China. Email: dzh666828@, wxwangst@, cskchung@.hk Received November 4th, 2010; revised January 5th, 2011; accepted January 19th, 2011 ABSTRACT Patterned-based time series segmentation (PTSS) is an important task for many time series data mining applications. In this paper, according to the characteristics of PTSS, a generalized model is proposed for PTSS. First, a new inter- pretation for PTSS is given by comparing this problem with the prototype-based clustering (PC). Then, a novel model, called clustering-inverse model (CI-model), is presented. Finally, two algorithms are presented to implement this model. Our experimental results on artificial and real-world time series demonstrate that the proposed algorithms are quite effective. Keywords : Pattern-Based Time Series Segmentation, Clustering-Inverse, Dynamic Time Warping, Perceptually Important Points, Evolution Computation, Particle Swarm Optimization, Genetic Algorithm 1. Introduction series set, a pattern time series also represents a tech- nique template, which indicates a representative time With the large amounts of time series data arising from series segment in a time series.