A Finite Precision LMS Algorithm for Increased Quantization Robustness

Document type: Conference Papers
Peer reviewed: Yes
Author(s): Fredric Lindström, Mattias Dahl, Ingvar Claesson
Title: A Finite Precision LMS Algorithm for Increased Quantization Robustness
Conference name: IEEE International Symposium on Circuits and Systems
Year: 2003
Pagination: IV365-IV368
Publisher: Institute of Electrical and Electronics Engineers Inc.
City: Bangkok,
Organization: Blekinge Institute of Technology
Department: Department of Telecommunications and Signal Processing (Institutionen för telekommunikation och signalbehandling)
Department of Telecommunications and Signal Processing S-372 25 Ronneby
+46 455 38 50 00
Language: English
Abstract: The well known Least Mean Square (LMS) algorithm, or variations thereof are frequently used in adaptive systems. When the LMS algorithm is implemented in a finite precision environment it suffers from quantization effects. These effects can severely degrade the performance of the algorithm. This paper proposes a modification of the LMS algorithm that reduces the impact of quantization at virtually no extra computational cost. The paper contains an off-line evaluation of a system identification scheme where the presented algorithm outperforms the classical LMS algorithm yielding a better modelling of the unknown plant. This approach is well suited for adaptive system identification, e.g. beam-forming, electrocardiography, and echo cancelling.
Subject: Signal Processing\General
Keywords: Digital signal processing, Robustness (control systems), Vectors, Algorithms
Edit