Title :
Identification of multivariate FIR systems using higher-order statistics
Author_Institution :
Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
The identification of multichannel moving average (MA) parameter matrices {H(k)} using fourth-order output cumulants is considered. By analysing the eigenstructures of the cumulant matrices, it is shown that the MA parameter matrices can be identified uniquely up to a post multiplication of monomial matrices if H(0) does not have columns that are pairwise colinear and H=[Ht(0),...,Ht(L)]t has full column rank. The constructive proof of this condition leads to a closed-form identification algorithm
Keywords :
FIR filters; MIMO systems; eigenvalues and eigenfunctions; filtering theory; higher order statistics; matrix algebra; moving average processes; parameter estimation; telecommunication channels; MA parameter matrices; MIMO MA process; blind system identification; cumulant matrices; eigenstructures; fourth-order output cumulants; full column rank matrix; higher-order statistics; monomial matrices; multichannel moving average parameter matrices; multivariate FIR system identification; pairwise colinear columns; post multiplication; Contracts; Equations; Erbium; Finite impulse response filter; Higher order statistics; Lungs; MIMO; Parameter estimation; Symmetric matrices; Systems engineering and theory;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.550195
