Real-Time TLS Algorithms in Gaussian and Impulse Noise Environments

Da-Zheng Feng (), Zheng Bao and Xian-Da Zhang
Additional contact information
Da-Zheng Feng: Xidian University, Key Lab. for Radar Signal Processing
Zheng Bao: Xidian University, Key Lab. for Radar Signal Processing
Xian-Da Zhang: Xidian University, Key Lab. for Radar Signal Processing

A chapter in Total Least Squares and Errors-in-Variables Modeling, 2002, pp 341-350 from Springer

Abstract: Abstract On the basis of the total minimum mean square error or the minimum Raleigh quotient, we propose a modified total least mean squares (TLMS) algorithm with the computational complexity close to the well-known LMS algorithm. A new fast RTLS algorithm is developed by using the recursive computation of the TLS solution for adaptive finite impulse response (FIR) filters. Using the shift structure of the augmented data vector, a fast algorithm for computing the new gain vector is given. The new fast algorithm is numerically stable and of computational complexity O (n). A recursive total instrumental-variable (RTIV) algorithm is given for finding the TLS solution to the over-determined normal equations, and its applications to adaptive IIR filtering are presented. Its arithmetic operation complexity is O (mn) (where m is the number of instrumental variables and n the dimension of the input-vector) per iteration. We give the L p -norm distance from a point to a hyper-plane. A real-time algorithm is introduced for finding the robust TLS solution in impulse noise, and has computational complexity O (n).

Keywords: total least mean squares; recursive least squares; instrumental variables; total L p -norm approximation; impulse noise; signal processing. (search for similar items in EconPapers)
Date: 2002
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-94-017-3552-0_30

Ordering information: This item can be ordered from
http://www.springer.com/9789401735520

DOI: 10.1007/978-94-017-3552-0_30

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().