Title :
A adaptive LMS algorithm with two transient factor
Author :
Zhaohua, Zeng ; Guizhong, Liu ; Shexiang, Ma
Author_Institution :
Inst. of Inf. Eng., Xi´´an Jiaotong Univ., China
Abstract :
A modified adaptive algorithm of smooth pseudo LMS (SPLMS) was presented by Zeng Zhaohua (see Electronic Science Journal, vol.20, no.4, p.566-69, 1998). Based on the SPLMS, a modified adaptive algorithm with two transient factors (DSPLMS) is proposed in this paper. Besides having the advantages of the LMS, it has a faster staring convergence rate, lower weight misadjustment, and better robustness against noise and disturbance. At the same time, this paper lays special emphasis on the transformation of two transient factors. The theoretical analysis is confirmed by the computer simulation results
Keywords :
adaptive filters; adaptive signal processing; convergence of numerical methods; filtering theory; least mean squares methods; noise; transients; SPLMS; adaptive LMS algorithm; adaptive filters; computer simulation results; convergence rate; disturbance robustness; modified adaptive algorithm; noise robustness; smooth pseudo LMS; transient factor; weight misadjustment; Adaptive algorithm; Adaptive filters; Computer simulation; Convergence; Inference algorithms; Iterative algorithms; Least squares approximation; Mean square error methods; Signal processing algorithms; Signal to noise ratio;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.894513
