Abstract | ||
---|---|---|
Change Point Discovery is a basic algorithm needed in many time series mining applications including rule discovery, motif discovery, casual analysis, etc. Several techniques for change point discovery have been suggested including wavelet analysis, cosine transforms, CUMSUM, and Singular Spectrum Transform. Of these methods Singular Spectrum Transform (SST) have received much attention because of its generality and because it does not require ad-hoc adjustment for every time se- ries. In this paper we show that traditional SST suers from two major problems: the need to specify five parameters and the rapid reduction in the specificity with increased noise levels. In this paper we define the Robust Singular Spectrum Transform (RSST) that alleviates both of these problems and compare it to RSST using dierent synthetic and real-world data series. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02568-6_13 | Industrial and Engineering Applications of Artificial Intelligence and Expert Systems |
Keywords | Field | DocType |
methods singular spectrum transform,time series,rule discovery,motif discovery,change point discovery,robust singular spectrum transform,casual analysis,real-world data series,singular spectrum transform,time series mining application,cosine transform,wavelet analysis | Singular value decomposition,Trigonometric functions,Computer science,Algorithm,Speech recognition,Data series,Singular spectrum analysis,Generality,Wavelet | Conference |
Volume | ISSN | Citations |
5579 | 0302-9743 | 15 |
PageRank | References | Authors |
0.78 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yasser F. O. Mohammad | 1 | 180 | 19.21 |
Toyoaki Nishida | 2 | 1097 | 196.19 |