On normalized data-reusing and affine-projections algorithms

This paper addresses the comparison between data-reusing LMS algorithms and the affine-projections algorithm. The normalized new data-reusing LMS (NNDR-LMS) algorithm, the binormalized data-reusing LMS (BNDR-LMS) algorithm, and the affine-projections (AP) algorithm are briefly presented within a common framework and their relationships are clarified. Topics such as equivalence of algorithms, graphical representation, and computational complexity are discussed.

[1]  P.S.R. Diniz,et al.  Colored input-signal analysis of normalized data-reusing LMS algorithms , 1998, 1998 IEEE International Conference on Electronics, Circuits and Systems. Surfing the Waves of Science and Technology (Cat. No.98EX196).

[2]  Timo I. Laakso,et al.  The Binormalized Data-Reusing LMS Algorithm with Optimized Step-Size Sequence , 1998 .

[3]  Bernard A. Schnaufer.  Practical techniques for rapid and reliable real-time adaptive filtering , 1995 .

[4]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[5]  S. Douglas.  The fast affine projection algorithm for active noise control , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[6]  José Antonio Apolinário,et al.  Convergence analysis of the binormalized data-reusing LMS algorithm , 2000, IEEE Trans. Signal Process..

[7]  José Antonio Apolinário,et al.  Mean-squared error analysis of the binormalized data-reusing LMS algorithm using a discrete-angular-distribution model for the input signal , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).