Title :
A study of the robustness of the M-Max NLMS adaptive algorithm
Author :
Mayyas, K. ; Aboulnasr, T. ; Eldos, T.
Author_Institution :
Dept. of Electr. Eng., Jordan Univ. of Sci. & Technol., Irbid, Jordan
Abstract :
In this paper, the M-Max NLMS algorithm is analyzed in a time-domain framework without constraining the number of updated coefficients per iteration or imposing statistical assumptions on the input signal. Analysis will prove the robustness of the M-Max NLMS algorithm under appropriate deterministic assumptions. Moreover, it will provide more insight into the algorithm structure leading to new choices of the step size for improved robust performance. A typical simulation example is presented to verify the deterministic findings
Keywords :
adaptive filters; filtering theory; least mean squares methods; time-domain analysis; M-Max NLMS adaptive algorithm; deterministic robustness study; robust performance; step size; time-domain framework; updated coefficients; Adaptive algorithm; Algorithm design and analysis; Computational modeling; Performance analysis; Robustness; Sampling methods; Signal analysis; Solids; Speech analysis; Time domain analysis;
Conference_Titel :
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-5471-0
DOI :
10.1109/ISCAS.1999.778808
