Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: basis functions

Sortuj według:

Ogranicz wyniki do:

Instantaneous Frequency Estimation of Multi-Component Non- Stationary Signals using Fourier Bessel series and Time-Varying Auto Regressive Model

Ravi Shankar Reddy G., Rao R.

International Journal of Electronics and Telecommunications

2015

Vol. 61, No. 4

365-376

In this paper, we propose a novel technique for Instantaneous frequency (IF) estimation of multi component non stationary signals using Fourier Bessel Series and Time-Varying Auto Regressive (FB-TVAR) model. In the proposed technique, the Fourier-Bessel (FB) expansion decomposes the multicomponent non stationary signal into a number of monocomponent signals and TVAR model is used to model each monocomponent signal. In TVAR modeling approach the time varying parameters are expanded as a linear combination of basis functions. In this paper, the TVAR parameters are expanded by a discrete cosine basis functions. The maximum likelihood estimation algorithm for model order selection in TVAR models is also discussed. The Instantaneous frequency (IF) is extracted from the time-varying parameters by calculating the angles of the estimation error filter polynomial roots. The estimation of the TVAR parameters of a multicomponent signal requires the inversion of a large covariance matrix, while the projected technique (FB-TVAR) requires the inversion of a number of comparatively small covariance matrices with better numerical stability properties. Simulation results are presented for three component discrete Amplitude and Frequency modulated (AM-FM)signal.

Dwuwymiarowa funkcja regresji opisana za pomocą bazowych funkcji sklejanych

Zellma M., Załęska-Fornal A.

Zeszyty Naukowe Akademii Marynarki Wojennej

2005

R. 46 nr 1 (160)

189-203

W artykule przedstawiono możliwości zastosowania bazowych funkcji sklejanych do wyznaczania dwuwymiarowej funkcji regresji metodą największej wiarygodności.

The paper presents some possibilities of applying the basic splines to determine the two dimentional regression function by means of the likelihood method.