Quadratic Estimation of Multivariate Signals from Randomly Delayed Measurements*

Authors:
S. Nakamori;A. Hermoso-Carazo;J. Linares-Pérez
Affiliations:
Department of Technology, Faculty of Education, Kagoshima University, Kagoshima, Japan 890-0065;Dpto. Estadística e I.O., Universidad de Granada, Granada, Spain;Dpto. Estadística e I.O., Universidad de Granada, Granada, Spain
Venue:
Multidimensional Systems and Signal Processing
Year:
2005

Citing 6
Cited 4

Polynomial Filtering for Linear Discrete Time Non-Gaussian Systems

SIAM Journal on Control and Optimization
Recursive estimator for linear and nonlinear systems with uncertain observations

Signal Processing
Real-Time Simultaneous Estimation and Decomposition ofRandom Signals

Multidimensional Systems and Signal Processing
Second-order polynomial estimators from uncertain observations using covariance information

Applied Mathematics and Computation
Baseband Volterra filters for implementing carrier basednonlinearities

IEEE Transactions on Signal Processing
Penalized least squares estimation of Volterra filters and higherorder statistics

IEEE Transactions on Signal Processing

Linear and quadratic least-squares estimation using measurements with correlated one-step random delay

Digital Signal Processing
Recursive estimation of discrete-time signals from nonlinear randomly delayed observations

Computers & Mathematics with Applications
Signal estimation with multiple delayed sensors using covariance information

Digital Signal Processing
Recursive least-squares quadratic smoothing from measurements with packet dropouts

Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses the least-squares quadratic estimation problem of a multivariate discrete signal, from noisy measurements which can be delayed by one sampling period. The delay in the observations is assumed to be random and the probability of a delay in each measurement is known. The quadratic recursive estimation algorithm, which uses only the delay probabilities and the moments (up to fourth-order) of the signal and noise-measurement, is derived from a linear estimation algorithm for a suitably defined augmented system.