Title :
Subspace methods for blind identification of multichannel FIR filters using space-time contraction of cumulants
Author :
Martone, Massimiliano
Author_Institution :
Telecommun. Group, Watkins-Johnson Co., Gaithersburg, MD, USA
fDate :
7/1/1998 12:00:00 AM
Abstract :
We show that the popular subspace method for identification of multichannel systems can be implemented using particular contractions of higher-order cumulants, in the case of independent, identically distributed (i.i.d.) inputs. The algorithm appears to outperform the traditional correlation-based subspace algorithm in low signal-to-noise-ratio (SNR) and/or correlated noise.
Keywords :
FIR filters; Gaussian noise; filtering theory; higher order statistics; identification; white noise; blind identification; correlated noise; higher-order cumulants; i.i.d. inputs; independent identically distributed inputs; low signal-to-noise-ratio; multichannel FIR filters; space-time contraction; subspace methods; Additive noise; Filtering; Finite impulse response filter; Gaussian noise; Higher order statistics; Matrix decomposition; Random variables; Signal to noise ratio; Statistical distributions;
Journal_Title :
Signal Processing Letters, IEEE