Recursive Estimation Algorithm Based on Covariances for Uncertainly Observed Signals Correlated with Noise

Seiichi NAKAMORI; Raquel CABALLERO-ÁGUILA; Aurora HERMOSO-CARAZO; José D. JIMÉNEZ-LÓPEZ; Josefa LINARES-PÉREZ

doi:10.1093/ietfec/e91-a.7.1706

Regular Section

Recursive Estimation Algorithm Based on Covariances for Uncertainly Observed Signals Correlated with Noise

Seiichi NAKAMORI, Raquel CABALLERO-ÁGUILA, Aurora HERMOSO-CARAZO, José D. JIMÉNEZ-LÓPEZ, Josefa LINARES-PÉREZ

Author information

Keywords: least-squares estimation, uncertain observations, signal-noise correlation, covariance information

JOURNAL RESTRICTED ACCESS

2008 Volume E91.A Issue 7 Pages 1706-1712

DOI https://doi.org/10.1093/ietfec/e91-a.7.1706

Details

Abstract

The least-squares linear filtering and fixed-point smoothing problems of uncertainly observed signals are considered when the signal and the observation additive noise are correlated at any sampling time. Recursive algorithms, based on an innovation approach, are proposed without requiring the knowledge of the state-space model generating the signal, but only the autocovariance and crosscovariance functions of the signal and the observation white noise, as well as the probability that the signal exists in the observations.

Corresponding author

Register with J-STAGE for free!