Signal Estimation Algorithm from Uncertain Observations with Signal and Coloured Noise Correlated at any Sampling Time

S. Nakamori (Japan), R. Caballero-Águila, A. Hermoso-Carazo, J. Jiménez-López, and J. Linares-Pérez (Spain)


Identification. Estimation. Filtering.


This paper addresses the least-squares linear filtering and fixed-point smoothing problems of signals from uncer tain observations perturbed by white plus coloured noises, when the variables describing the uncertainty are indepen dent and the signal is correlated with the coloured noise. Using an innovation approach, recursive filtering and fixed point smoothing algorithms are derived, without requiring the knowledge of the state-space model generating the sig nal, but only covariance information of the signal and the observation noises, as well as the probability that the signal exists in the observations.

Important Links:

Go Back