Abstract
The statistical description of the Sampling-Reconstruction Procedure (SRP) of non-Gaussian stochastic processes is described. The method of investigation is based on the conditional mean rule. There is discussion of the general formulas of the SRP of the output process realizations of nonlinear non-memory converters, when the input is an arbitrary process. The set of samples is arbitrary. Three types of non-linear characteristics of converters are considered: polynomial, exponential, and piece-wise linear. General expressions are specified for the case of Gaussian input processes. An SRP statistical description is presented for non-Gaussian continuous Markovian process realizations. The SRP of Markovian process realizations with jumps is considered in detail. In all cases, reconstruction and reconstruction error functions are found.
Original language | English |
---|---|
Title of host publication | Probability |
Subtitle of host publication | Interpretation, Theory and Applications |
Publisher | Nova Science Publishers, Inc. |
Pages | 299-326 |
Number of pages | 28 |
ISBN (Print) | 9781621002499 |
State | Published - Jan 2012 |
Keywords
- Non-Gaussian process
- Reconstruction
- Reconstruction error
- Sampling