A novel method for time series symbolization based on singular event features clustering

Author

Qu, Wenlong ; He, Yichao ; Qu, Wenjing

Author_Institution

Inf. Eng. Sch., Shijiazhuang Univ. of Econ., Shijiazhuang, China

Volume

1

fYear

2010

fDate

21-24 May 2010

Abstract

This Qualitative abstract representation of time series is a precondition of pattern discovery. A novel method for time series symbolization based on singular event features clustering is proposed in this paper. The first step of it is to extract singular event features based on multi-scale wavelet which can divide time series into event sequences with independent trend. Secondly, cluster the events that represented by transform parameters through the novel fuzzy immune genetic algorithm to implement symbolization. Each event is identified by the cluster it belongs to. The proposed method is applied to unstable financial time series symbolization. The proposed method can be used to discover significant similar patterns, classification and associated patterns from time series.

Keywords

data analysis; data mining; fuzzy set theory; genetic algorithms; pattern clustering; statistical analysis; time series; wavelet transforms; classification; event sequences; feature extraction; fuzzy immune genetic algorithm; multiscale wavelet; pattern discovery; qualitative abstract representation; singular event features clustering; time series symbolization; Clustering algorithms; Data analysis; Data mining; Equations; Feature extraction; Genetic algorithms; Helium; Mathematics; Pattern analysis; Piecewise linear techniques; data mining; singular event; symbolization; time series;

fLanguage

English

Publisher

ieee

Conference_Titel

Future Computer and Communication (ICFCC), 2010 2nd International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-5821-9

Type

conf

DOI

10.1109/ICFCC.2010.5497819

Filename

5497819