Logo image
Estimation of large sets of stochastic signals: The case of sparse sampling
Journal article   Peer reviewed

Estimation of large sets of stochastic signals: The case of sparse sampling

A. Torokhti, P. Howlett and H. Laga
Sampling Theory in Signal and Image Processing, Vol.13(3), pp.207-230
2014

Abstract

In many applications, a priori information on a large set of signals of interest can only be obtained for a few signals, p, while information on other signals is missing. At the same time, it is required to estimate each reference signal. The signal is a stochastic vector and the observations are noisy. The conceptual foundation of the proposed filter is an optimal least squares linear estimate of the incremental change to the p signal pairs, extended by a natural interpolation to an estimated value of each reference signal. The new filter is expressed in terms of the Moore-Penrose pseudo-inverse matrices and therefore is always well-defined.

Details

Metrics

43 Record Views
Logo image