Statistical Interface for Chaotic Signal in Noise

摘要

A method for determining the frequency of a real sinusoid is proposed. Based onexponential sampling of the waveform, the approach requires virtually no computation. It can be easily implemented in digital hardware. A dynamic programming algorithm and a suboptical kit computationally efficient method for estimation of a chaotic signal in white Gaussian noise are proposed. The nonlinear map is assumed known so that only the Initial condition need be estimated. Computer simulations confirm that both approaches produces efficient estimates at high signal-to-noise ratios. (AN).