TY - GEN
T1 - Natural gradient for temporally dependent component analysis
AU - Shi, Zhenwei
AU - Cheng, Dalong
AU - Tan, Xueyan
AU - Jiang, Zhiguo
PY - 2010
Y1 - 2010
N2 - The temporally dependent component analysis (TDCA) method for blind source separation (BSS) is introduced. As a new principle, it is shown that maximizing the mapping of autocorrelation of source signals can be used to perform BSS. We use the natural gradient algorithm for TDCA and study the mathematical properties of TDCA. Simulations by square temporal autocorrelation sources verify the efficient implementation of the proposed method.
AB - The temporally dependent component analysis (TDCA) method for blind source separation (BSS) is introduced. As a new principle, it is shown that maximizing the mapping of autocorrelation of source signals can be used to perform BSS. We use the natural gradient algorithm for TDCA and study the mathematical properties of TDCA. Simulations by square temporal autocorrelation sources verify the efficient implementation of the proposed method.
KW - Blind source separation (BSS)
KW - Independent component analysis (ICA)
KW - Linear autocorrelation
KW - Nonlinear autocorrelation
UR - https://www.scopus.com/pages/publications/78149352936
U2 - 10.1109/ICNC.2010.5583820
DO - 10.1109/ICNC.2010.5583820
M3 - 会议稿件
AN - SCOPUS:78149352936
SN - 9781424459612
T3 - Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010
SP - 972
EP - 975
BT - Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010
T2 - 2010 6th International Conference on Natural Computation, ICNC'10
Y2 - 10 August 2010 through 12 August 2010
ER -