國立臺灣大學資訊工程學系Chang, Ming-WeiMing-WeiChangLin, Chih-JenChih-JenLinWeng, R.C.R.C.Weng2006-09-272018-07-052006-09-272018-07-052002-01-23http://ntur.lib.ntu.edu.tw//handle/246246/2006092712285907084We present a framework for the unsupervised segmentation of time series using support vector regression. It applies to non-stationary time series which alter in time. We follow the architecture by Pawelzik et al. which consists of competing predictors. In competing Neural Networks were used while here we exploit the use of Support Vector Machines, a new learning technique. Results indicate that the proposed approach is as good as that in . Diferences between the two approaches are also discussed.application/pdf374119 bytesapplication/pdfzh-TWreporthttp://ntur.lib.ntu.edu.tw/bitstream/246246/2006092712285907084/1/ijcnntime.pdf