Asymptotic behavior of order statistic least mean square (OSLMS) algorithms in nonGaussian environments

  • Authors:

  • Yifeng Fu;Geoffrey A. Williamson

  • Affiliations:

  • Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, Illinois;Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, Illinois

  • Venue:
  • ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: digital speech processing - Volume III
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

Asymptotic behavior is studied for a class of Order Statistic Least Mean Square (OSLMS) algorithms. These algorithms modify the ordinary Least Mean Square (LMS) algorithm by applying an order statistic (OS) filtering operation to the instantaneous gradient estimate. The OS operation in OSLMS can reduce the bias on filter coefficient estimates (relative to LMS) when operating in nonguassian environments and also can reduce the average squared parameter error when in steady state operation. Some supporting analysis is presented for these effects, and simulation studies are provided. Guidelines are suggested for the selection of the OSLMS algorithms based on the expected noise environment.