In this work the problem of reconstruction of an original complex-valued signal ot, t = 0, 1,...,n - 1, from its Discrete Fourier Transform (DFT) spectrum corrupted by random fluctuations of magnitude and/or phase is investigated. It is assumed that the magnitude and/or phase of discrete spectrum values are distorted by realizations of uncorrelated random variables. The obtained results of analysis of signal reconstruction from such distorted DFT spectra concern derivation of the expected values and bounds on variances of the reconstructed signal at the observation moments. It is shown that the considered random distortions in general entail change in magnitude and/or phase of the reconstructed signal expected values, which together with imposed random deviations with finite variances can blur the similarity to the original signal. The effect of analogous random amplitude and/or phase distortions of a complex valued time domain signal on band pass filtration of distorted signal is also investigated.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this work the problem of characterization of Discrete Fourier Transform (DFT) spectrum of an original complex-valued signal modulated by random fluctuations of amplitude and phase is investigated. It is assumed that the amplitude and phase of signal values at discrete time moments of observations are distorted by adding realizations of independent and identically distributed random variables. The obtained results of theoretical analysis of such distorted signal spectra show that only in the case of amplitude modulation the DFT spectrum of the modulated bounded signal can be similar to the original signal spectrum, although there occur random deviations. On the other hand, if phase modulation is present, then the DFT spectrum of the modulated bounded signal not only shows random deviations but also amplitudes of peaks existing in the original spectrum are diminished, and consequently similarity to the original signal spectrum can be significantly blurred.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this work theoretical aspects of the Fourier Transform Band Pass Filter (FTBPF) technique are investigated which show that such a procedure is applicable to extraction of irregular monochromatic oscillations with time-varying amplitudes from the analyzed signal data. Considerations concerning the boundary effects occurring in numerical implementation of the FTBPF are included which indicate that the filter transfer function smoothness influences boundary effects magnitude. The possibility of using the studied filtration technique for recognition of elliptical oscillation polarization is envisaged and an estimate of oscillation polarization classification error is derived.
In this work theoretical foundations of the Fourier Transform Band Pass Filter (FTBPF) technique are developed which show that such procedure is applicable to extraction of irregular monochromatic oscillations with time-varying amplitudes and phases from the analyzed signal data. Considerations concerning the statistical error of the FTBPF coherence between two filtered oscillations are included. Further certain method of the filter pass-band width parameter determination is proposed and relation between applying the FTBPF to realvalued signals and forming the so called complex-valued analytic oscillations based on the Hilbert transform is indicated.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.