Robust Functional Supervised Classification for Time Series
- 274 Downloads
We propose using the integrated periodogram to classify time series. The method assigns a new time series to the group that minimizes the distance between the series integrated periodogram and the group mean of integrated periodograms. Local computation of these periodograms allows the application of this approach to nonstationary time series. Since the integrated periodograms are curves, we apply functional data depth-based techniques to make the classification robust, which is a clear advantage over other competitive procedures. The method provides small error rates for both simulated and real data. It improves existing approaches and presents good computational behavior.
KeywordsTime series Supervised classification Integrated periodogram Functional data depth
Unable to display preview. Download preview PDF.
- ALONSO, A.M., CASADO, D., LÓPEZ-PINTADO, S. and ROMO, J. (2008), “A Functional Data Based Method for Time Series Classification”, Working Paper, Departamento de Estadística. Universidad Carlos III deMadrid, available at http://hdl.handle.net/10016/3381.
- BIAU, G., BUNEA, F., andWEGKAMP, M.H. (2003), “Functional Classification in Hilbert Spaces”, IEEE Transactions on Information Theory, 1(11), 1–8.Google Scholar
- BLANDFORD, R.R. (1993), “Discrimination of Earthquakes and Explosions at Regional Distances Using Complexity”, Report AFTAC-TR-93-044 HQ, Air Force Technical Applications Center, Patrick Air Force Base, FL.Google Scholar
- CASADO, D. (2013), StatisCLAS: Methods for Statistical Classification, Package of code, available at http://www.casado-d.org/edu/publications.html#Code.
- CLEVELAND, R.B., CLEVELAND, W.S., MCRAE, J.E., and TERPENNING, I. (1990), “STL: A Seasonal-Trend Decomposition Procedure Based on Loess”, Journal of Official Statistics, 6, 2–73.Google Scholar
- DAHLHAUS, R. (1996), “Asymptotic Statistical Inference for Nonstationary Processes with Evolutionary Spectra”, in Athens Conference on Applied Probability and Time Series Analysis, eds. P.M. Robinson and M. Rosenblatt, New York: Springer.Google Scholar
- LÓPEZ-PINTADO, S., and ROMO, J. (2006), “Depth-Based Classification for Functional Data”, DIMACS Series in Discrete Mathematics and Theoretical Computer Science (Vol. 72), Providence RI: American Mathematical Society.Google Scholar