TY - JOUR
T1 - Multikernel adaptive filtering
AU - Yukawa, Masahiro
N1 - Funding Information:
Manuscript received June 14, 2011; revised November 09, 2011 and February 23, 2012; accepted May 05, 2012. Date of publication May 22, 2012; date of current version August 07, 2012. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Suleyman S. Kozat. This work was supported by KDDI Foundation. A preliminary version of this work was presented at the European Signal Processing Conference (EUSIPCO), 2011.
PY - 2012
Y1 - 2012
N2 - This paper exemplifies that the use of multiple kernels leads to efficient adaptive filtering for nonlinear systems. Two types of multikernel adaptive filtering algorithms are proposed. One is a simple generalization of the kernel normalized least mean square (KNLMS) algorithm , adopting a coherence criterion for dictionary designing. The other is derived by applying the adaptive proximal forward-backward splitting method to a certain squared distance function plus a weighted block l 1 norm penalty, encouraging the sparsity of an adaptive filter at the block level for efficiency. The proposed multikernel approach enjoys a higher degree of freedom than those approaches which design a kernel as a convex combination of multiple kernels. Numerical examples show that the proposed approach achieves significant gains particularly for nonstationary data as well as insensitivity to the choice of some design-parameters.
AB - This paper exemplifies that the use of multiple kernels leads to efficient adaptive filtering for nonlinear systems. Two types of multikernel adaptive filtering algorithms are proposed. One is a simple generalization of the kernel normalized least mean square (KNLMS) algorithm , adopting a coherence criterion for dictionary designing. The other is derived by applying the adaptive proximal forward-backward splitting method to a certain squared distance function plus a weighted block l 1 norm penalty, encouraging the sparsity of an adaptive filter at the block level for efficiency. The proposed multikernel approach enjoys a higher degree of freedom than those approaches which design a kernel as a convex combination of multiple kernels. Numerical examples show that the proposed approach achieves significant gains particularly for nonstationary data as well as insensitivity to the choice of some design-parameters.
KW - Block soft-thresholding operator
KW - kernel adaptive filtering
KW - reproducing kernel Hilbert space
UR - http://www.scopus.com/inward/record.url?scp=84865211015&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84865211015&partnerID=8YFLogxK
U2 - 10.1109/TSP.2012.2200889
DO - 10.1109/TSP.2012.2200889
M3 - Article
AN - SCOPUS:84865211015
SN - 1053-587X
VL - 60
SP - 4672
EP - 4682
JO - IEEE Transactions on Acoustics, Speech, and Signal Processing
JF - IEEE Transactions on Acoustics, Speech, and Signal Processing
IS - 9
M1 - 6203609
ER -