Title :
Efficient tracking of time-varying signal subspaces
Author :
Davila, C.E. ; Mobin, M.S.
Author_Institution :
Dept. of Electr. Eng., Southern Methodist Univ., Dallas, TX, USA
Abstract :
An algorithm for tracking d principal eigenvectors of an M-dimensional sample data covariance matrix is described. This algorithm requires O(Md2) multiplications per iteration yet has performance comparable to algorithms having O (M2d2) complexity. A proof of the algorithm´s convergence is given along with the results of several computer simulations
Keywords :
matrix algebra; signal processing; tracking; algorithm; computer simulations; convergence; multiplications; sample data covariance matrix; signal processing; time-varying signal subspaces; Computational complexity; Convergence; Covariance matrix; Eigenvalues and eigenfunctions; Kalman filters; Performance gain; Polynomials; Signal processing; Signal processing algorithms; White noise;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226640
