Discriminant analysis based on binary time series
- 16 Downloads
Binary time series can be derived from an underlying latent process. In this paper, we consider an ellipsoidal alpha mixing strictly stationary process and discuss the discriminant analysis and propose a classification method based on binary time series. Assume that the observations are generated by time series which belongs to one of two categories described by different spectra. We propose a method to classify into the correct category with high probability. First, we will show that the misclassification probability tends to zero when the number of observation tends to infinity, that is, the consistency of our discrimination method. Further, we evaluate the asymptotic misclassification probability when the two categories are contiguous. Finally, we show that our classification method based on binary time series has good robustness properties when the process is contaminated by an outlier, that is, our classification method is insensitive to the outlier. However, the classical method based on smoothed periodogram is sensitive to outliers. We also deal with a practical case where the two categories are estimated from the training samples. For an electrocardiogram data set, we examine the robustness of our method when observations are contaminated with an outlier.
KeywordsStationary process Spectral density Binary time series Robustness Discriminant analysis Misclassification probability
Mathematics Subject Classification62H30 62G86
The authors are grateful to the editor in chief Professor Hajo Holzmann, the anonymous associate editor, and two referees for their instructive comments and kindness. The first author Y.G. thanks Doctor Fumiya Akashi for his encouragements and comments and was supported by Grant-in-Aid for JSPS Research Fellow Grant Number JP201920060. The second author M.T. was supported by the Research Institute for Science & Engineering of Waseda University and JSPS Grant-in-Aid for Scientific Research (S) Grant Number JP18H05290.
Compliance with ethical standards
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
- Billinsley P (1968) Convergence of probability measures. Wiley, New YorkGoogle Scholar
- Buz A, Litan C (2012) What properties do clipped data inherit from the generating processes? Studia Universitatis Babes-Bolyai 57(3):85–96Google Scholar
- Dau HA, Keogh E, Kamgar K, Yeh CCM, Zhu Y, Gharghabi S, Ratanamahatana CA, Chen Y, Hu B, Begum N, Bagnall A, Mueen A, Batista G (2018) The UCR time series classification archive. https://www.cs.ucr.edu/~eamonn/time_series_data_2018/
- Dette H, Hallin M, Kley T, Volgushev S (2015) Of copulas, quantiles, ranks and spectra: An \(l_1\)-approach to spectral analysis. Bernoulli 21(2):781–831Google Scholar
- He S, Kedem B (1989) On the Stieltjes–Sheppard orthant probability formula. Tech Rep tr-89-69, Dept. Mathematics, Unvi. Maryland, College ParkGoogle Scholar
- Kedem B, Li T (1989) Higher order crossings from a parametric family of linear filters. Tech Rep tr-89-47, Dept. Mathematics, Unvi. Maryland, College ParkGoogle Scholar
- Kley T (2014) Quantile-based spectral analysis. Ph.D. thesis, Ruhr-Universitut BochumGoogle Scholar
- Olszewski R T (2001) Generalized feature extraction for structural pattern recognition in time-series datas. Ph.D. thesis, Carnegie Mellon UniversityGoogle Scholar