Title :
Finding initial values for time-varying joint diagonalization
Author :
Hori, Gen ; Tanaka, Toshihisa
Author_Institution :
Fac. of Bus. Adm., Asia Univ., Musashino, Japan
Abstract :
A novel method termed differential joint diagonalization (DJD) is introduced to find good initial values for joint diagonalization of time-varying correlation matrices. A key point of the method is finding a matrix which satisfies several conditions in the form of the matrix Riccati equation simultaneously. An alternate algorithm of differential joint diagonalization and joint diagonalization is proposed and shown by numerical simulation to outperform a standard joint diagonalization algorithm in tracking time-varying mixing models.
Keywords :
Riccati equations; blind source separation; matrix algebra; BSS algorithms; blind signal separation algorithms; differential joint diagonalization; matrix Riccati equation; numerical simulation; time-varying correlation matrices; time-varying joint diagonalization; Agriculture; Asia; Blind source separation; Convergence; Linear approximation; Matrices; Numerical simulation; Riccati equations; Signal processing algorithms; Source separation; Joint diagonalization; signal separation; time-varying mixing models;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5494925
