Analysis of Variable Step-size Order Statistic LMS-based Algorithms with a Data-reuse Factor

Suchada Sitjongsataporn

Centre of Electronic Systems Design and Signal Processing (CESdSP)

Department of Electronic Engineering, Mahanakorn University of Technology

140 Cheumsamphan Road, Bangkok 10530 Thailand

E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Kodchakorn Na Nakornphanom

School of Science and Technology, Sukhothai Thammathirat Open University

9/9 Chaengwattana Road, Nonthaburi 11120 Thailand

E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Manuscript received January 11, 2013

Revised February 14, 2013


ABSTRACT

In this paper, we present variable step-size algorithms based on an order statistic normalized averaged least mean square (OS-NALMS) with a data-reuse factor. An optimal step-size parameter is investigated by means of mean square deviation criterion, we then modify in the recursion form. Two of new variable step-size approaches are introduced with regard to the optimal step-size algorithm. In order to reduce the complexity, a variable data-reuse factor approach is applied to the number of reused gradient based estimate sequences for averaged least mean square algorithm. Simulation results demonstrate that the performance of proposed variable step-size OS-NALMS algorithms can obtain in terms of fast convergence and robustness.

 

Keywords: Adaptive filters, variable step-size algorithm, order statistic mechanism, least mean square (LMS) algorithm, data-reuse factor.

mutengineer@gmail.com

Mahanakorn University of Technology

140 Moo 1, Cheum-Sampan Road, Nongchok, Bangkok, Thailand 10530

Tel: +(662)988-3655  Fax: +(662)988-4027

designed by sutit.ongart@gmail.com