Local Analysis of Long Range Dependence Based on Fractional Fourier Transform

The long range dependence (LRD) of stationary process is characterized by the Hurst parameter. In practice, previous methods for estimation of the Hurst parameter might have poor performance when processing the non-stationary time series or trying to distinguish the slight difference between very long stochastic processes. This paper explores the use of fractional Fourier transform (FrFT) for estimating the Hurst parameter. The time series was processed locally to achieve a reliable local estimation of the Hurst parameter. The biocorrosion signal which is very popular in biological engineering was studied as an example to show the long range dependence properties. After comparing with the commonly used wavelet based method and another method based on Matlab's polyfit, the new Hurst parameter estimator proposed in this paper is proved to be more robust for non-stationarity and can show the slight difference clearly between those very long sets of biocorrosion data

[1]  H. Ozaktas,et al.  Fractional Fourier transforms and their optical implementation. II , 1993 .

[2]  D. Timmermann,et al.  Intrinsic Flexibility and Robustness in Adaptive Systems: A Conceptual Framework , 2006, 2006 IEEE Mountain Workshop on Adaptive and Learning Systems.

[3]  Gennady Samorodnitsky,et al.  Long range dependence in heavy tailed stochastic processes , 2001 .

[4]  J. Geweke,et al.  THE ESTIMATION AND APPLICATION OF LONG MEMORY TIME SERIES MODELS , 1983 .

[5]  J. S. Marron,et al.  LASS: a tool for the local analysis of self-similarity , 2006, Comput. Stat. Data Anal..

[6]  Z. Zalevsky,et al.  The Fractional Fourier Transform: with Applications in Optics and Signal Processing , 2001 .

[7]  Nephi A. Zufelt,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[8]  Murad S. Taqqu,et al.  Strengths and Limitations of the Wavelet Spectrum Method in the Analysis of Internet Traffic , 2004 .

[9]  P. Robinson.  Gaussian Semiparametric Estimation of Long Range Dependence , 1995 .

[10]  Patrice Abry,et al.  A Wavelet-Based Joint Estimator of the Parameters of Long-Range Dependence , 1999, IEEE Trans. Inf. Theory.

[11]  Levent Onural,et al.  Convolution, filtering, and multiplexing in fractional Fourier domains and their relation to chirp and wavelet transforms , 1994 .

[12]  YangQuan Chen,et al.  ELECTROCHEMICAL NOIS E SIGNAL PROCESSING USING R/S ANALYSIS AND FRACTIONAL FOURIER TRANSFORM , 2006 .

[13]  J. S. Marron,et al.  On the wavelet spectrum diagnostic for Hurst parameter estimation in the analysis of Internet traffic , 2005, Comput. Networks.

[14]  H. J. Caulfield,et al.  Wavelet processing and optics , 1996, Proc. IEEE.

[15]  Yao Li,et al.  Wavelet-based signal processing and optics , 1994, Other Conferences.

[16]  Patrice Abry,et al.  Wavelet Analysis of Long-Range-Dependent Traffic , 1998, IEEE Trans. Inf. Theory.