Abo Bibliothek: Guest
Journal of Automation and Information Sciences

Erscheint 12 Ausgaben pro Jahr

ISSN Druckformat: 1064-2315

ISSN Online: 2163-9337

SJR: 0.173 SNIP: 0.588 CiteScore™:: 2

Indexed in

Properties of LSM-Estimator of Correlation Function of Biperiodically Correlated Random Processes

Volumen 52, Ausgabe 6, 2020, pp. 44-57
DOI: 10.1615/JAutomatInfScien.v52.i6.40
Get accessGet access

ABSTRAKT

Recurrence and stochasticity are the features of many oscillation processes which occur in the different fields of science and techniques. Nowadays the models in the form of periodically correlated random processes (PCRP) are successfully used for the analysis of these processes. PCRP-approach provided more efficient solution to problem of signal transformation in communication theory, technical and medical diagnosis, energetics, forecasting of geophysical processes. Based on the experimental data coherent and component methods, the least square method, the linear filtration method have been developed for estimating correlation and spectral characteristics of PCRP. However, when analyzing oscillations there are situations when stochastic recurrence of one period interacts with stochastic recurrence of other. To analyze properties of double rythmicity the use is made of its models in the form of biperiodically correlated random processes (BPCRP). With close combination frequencies the application of the component method for estimating BPCRP characteristics can lead to significant leakage errors. As shown in this paper using the least square method helps to avoid these errors. Analysis of features of correlation functions estimates was carried out based on solution of the matrix equation providing the necessary conditions for the quadratic functional minimum. An expression is obtained for biasing estimates arising due to a preliminary definition of mathematical expectation. It is shown that the condition for the asymptotical unbiasedness of estimates is the attenuation of the correlation relationship with an increase in the bias. This condition also provides the mean square convergence of estimates for Gaussian BPCRP. Expression for the variance of LSM-estimator of correlation function compared with the variance of the component estimator contains additional components dependent of combinative frequencies and tending to zero when the length of realization is growing. Consideration was given to the example of LSM-estimating the correlation function of quadrature BPCRP-model and the comparison of efficiency of component and LSM-estimators was carried out.

REFERENZEN
  1. Cyclostationarity in communications and signal processing, Ed. by W.A. Gardner, IEEE Press, New York, 1994.

  2. Hurd H.L., Miamee A., Periodically correlated random sequences. Spectral theory and practice, Wiley-Interscience, New Jersey, 2007.

  3. Gardner W.A., Napolitano A., Paura L., Cyclostationarity: Half a century of research, Signal Processing, 2006, 86, 639-697, DOI: 10.1016/j.sigpro.2005.06.016.

  4. Javorskyj I.M., Mathematical models and analysis of stochastic oscillations [in Ukrainian], FMI NAN Ukrainy, Lviv, 2013.?.

  5. Napolitano A., Cyclostationarity: New trends and application, Signal Processing, 2016, DOI: 10.1016/ j.sigpro.2015.09.011.

  6. Gardner W.A., Exploitation of spectral redundancy in cyclostationary signals, IEEE SP Magazine, 1991, 8, No. 2, 14-36, DOI: 10.1109/79.81007.

  7. Napolitano A., Generalizations of cyclostationarity signal processing: Spectral analysis and applications, Wiley-IEEE Press, 2012, DOI: 10.1002/9781118437926.

  8. Antoni J., Cyclostationarity by examples, Mechanical Systems and Signal Processing, 2009, 23, 987-1036, DOI: 10.1016/j.ymssp.2008.10.010.

  9. Javorskyj I., Yuzefovych R., Kravets I., Matsko I., Properties of characteristics estimators of periodically correlated random processes in preliminary determination of the period of correlation, Radioeiectronics and Communications Systems, 2012, 55, 335-348. DOI: 10.3103/S0735272712080018.

  10. Javorskyj I.M., Dzeryn O.Yu., Yuzefovych R.M., Analysis of mean function discrete LSM-estimator for biperiodically nonstationary random signals, Mathematical Modeling and Computing, 2019, 6, No. 1, 44-57, DOI: 10.23939/mmc2019.01.044.

  11. Javorskyj I., Yuzefovych R., Kravets I., Matsko I., Methods of periodically correlated random processes and their generalizations, Lecture Notes in Mechanical Engineering, 2014, 73-93, DOI: 10.1007/978-3-319-04187-2_6.

  12. Javorskyj I., Matsko I., Yuzefovych R., Zakrzewski Z., Discrete estimators of characteristics for periodically correlated time series, Digital Signal Processing: A Review Journal, 2016, 53, 25-40, DOI: 10.1016/j.dsp.2016.03.003.

REFERENZIERT VON
  1. Andreykiv Oleksandr, Dolinska Iryna, Hembara Nazar, Svirchevskyi Orest, Kopnicky Miroslav, Budayova Zuzana, Mathematical Modeling of Aging Processes of Pipeline Materials and Estimation of their Residual Lifetime, 2022 12th International Conference on Advanced Computer Information Technologies (ACIT), 2022. Crossref

  2. Aliev T. A., Musaeva N. F., Quluyev Q. A., Rzayeva N. E., Technologies for Analyzing and Calculating the Relationship between the Useful Component and the Noise of Noisy Signal in Monitoring Systems, Mekhatronika, Avtomatizatsiya, Upravlenie, 23, 12, 2022. Crossref

Digitales Portal Digitale Bibliothek eBooks Zeitschriften Referenzen und Berichte Forschungssammlungen Preise und Aborichtlinien Begell House Kontakt Language English 中文 Русский Português German French Spain