Distributed optimal component fusion deconvolution filtering

Authors:
Shu-Li Sun
Affiliations:
Department of Automation, Heilongjiang University, Harbin, People's Republic of China
Venue:
Signal Processing
Year:
2007

Citing 4
Cited 0

Multisensor optimal information fusion input white noise deconvolution estimators

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Technical Communique: Multi-sensor information fusion white noise filter weighted by scalars based on Kalman predictor

Automatica (Journal of IFAC)
Multi-sensor optimal information fusion Kalman filter

Automatica (Journal of IFAC)
Optimal linear estimation fusion .I. Unified fusion rules

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.08

Visualization

Abstract

Using the state and white noise filters, a distributed optimal fusion deconvolution filter weighted by scalars is given for every signal component of discrete multichannel autoregressive moving average (ARMA) signal measured by multiple sensors. Under scalar weighting condition, it is optimal in the linear minimum variance (LMV) sense. Every signal component is estimated by scalar weighting fusion from local filters of the same component. The fusion filter of every signal component has higher precision than any local filter of the corresponding signal component does. Compared with the fusion filter weighted by matrices, it can reduce the computational burden since it only requires the computation of scalar weights. The signal filtering error cross-covariance between any two sensors is derived. Applying it to a double-channel signal system with three sensors shows the effectiveness.