×

Time series classification based on spectral analysis. (English) Zbl 1132.62078

Summary: For time series data with obvious periodicity (e.g., electric motor systems and cardiac monitor data) or vague periodicity (e.g., earthquake and explosion, speech, and stock data), frequency-based techniques using the spectral analysis can usually capture the features of the series. By this approach, we are able not only to reduce the data dimensions in the frequency domain but also utilize these frequencies by general classification methods such as linear discriminant analysis (LDA) and \(k\)-nearest-neighbors (KNN) to classify the time series. This is a combination of two classical approaches. However, there is a difficulty in using LDA and KNN in frequency domains due to excessive dimensions of data. We overcome the obstacle by using singular value decomposition to select essential frequencies. Two data sets are used to illustrate our approach. The classification error rates of our simple approach are comparable to those of several more complicated methods.

MSC:

62M15 Inference from stochastic processes and spectral analysis
62H30 Classification and discrimination; cluster analysis (statistical aspects)
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)

Software:

ElemStatLearn
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Box G. E. P., Time Series Analysis: Forecasting and Control () (1976) · Zbl 0363.62069
[2] Box G. E. P., Time Series Analysis: Forecasting and Control., 3. ed. (1994) · Zbl 0858.62072
[3] DOI: 10.1109/TIT.1967.1053964 · Zbl 0154.44505 · doi:10.1109/TIT.1967.1053964
[4] Demerdash N. A., Proceedings of the Naval Symposium for Electric Machines pp 235– (1997)
[5] Demmel J. W., Applied Numerical Linear Algebra (1997) · Zbl 0879.65017
[6] DOI: 10.1111/j.1469-1809.1938.tb02189.x · Zbl 0019.35703 · doi:10.1111/j.1469-1809.1938.tb02189.x
[7] Gardner W. A., Statistical Spectral Analysis. A Non-Probabilistic Theory (1988) · Zbl 0652.62090
[8] Gentle J. E., Numerical Linear Algebra for Applications in Statistics (1998) · Zbl 0908.65015
[9] Giudici P., Applied Data Mining: Statistical Methods for Business and Industry (2003) · Zbl 1067.62004
[10] Harville D. A., Matrix Algebra from a Statistician’s Perspective (1997) · Zbl 0881.15001
[11] Hastie T., The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2001) · Zbl 0973.62007
[12] DOI: 10.1198/016214504000001105 · Zbl 1117.62357 · doi:10.1198/016214504000001105
[13] DOI: 10.2307/2669629 · Zbl 0906.62060 · doi:10.2307/2669629
[14] Lin C. T., Neural Fuzzy Systems – A Neuro-Fuzzy Synergism to Intelligent Systems (1996)
[15] DOI: 10.1109/TKDE.2004.17 · Zbl 05109795 · doi:10.1109/TKDE.2004.17
[16] Shumway R. H., Applied Statistical Time Series Analysis (1988)
[17] Wei W. W. S., Time Series Analysis: Univariate and Multivariate Methods (1989)
[18] Zivot E., Modelling Financial Time Series with S-Plus (2002) · Zbl 1038.91071
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.