2006 IEEE International Symposium on Circuits and Systems
DOI: 10.1109/iscas.2006.1692576
|View full text |Cite
|
Sign up to set email alerts
|

A Set-Membership NLMS Algorithm with Time-Varying Error Bound

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
15
0
8

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 23 publications
(24 citation statements)
references
References 5 publications
1
15
0
8
Order By: Relevance
“…The SNR was set in 20 dB and the upper bound γ for the construction of the constraint sets related to the SM-PUAP was chosen to be γ = 2 σ 2 z . This value coincides with those suggested in the literature [24]. The simulations consisted of 1000 independent runs, and the average performance is computed.…”
Section: Simulation Results and Discussionsupporting
confidence: 86%
See 2 more Smart Citations
“…The SNR was set in 20 dB and the upper bound γ for the construction of the constraint sets related to the SM-PUAP was chosen to be γ = 2 σ 2 z . This value coincides with those suggested in the literature [24]. The simulations consisted of 1000 independent runs, and the average performance is computed.…”
Section: Simulation Results and Discussionsupporting
confidence: 86%
“…Setting a value too small for γ might lead to an empty set of feasible solutions, whereas setting a value too big might lead to inconsistent estimates. Some rules of the thumb have been suggested in the setmembership filtering literature in order to choose this upper bound properly [23], [24].…”
Section: B Set-membership Filteringmentioning
confidence: 99%
See 1 more Smart Citation
“…The first inequality follows from the fact that we do not know exactly what will happen with w(k +1) 2 when an update occurs andẽ 2 (k) < n 2 (k) at the same time 1 , and therefore, it corresponds to a pessimistic bound. The second inequality is trivial and the subsequent equality follows from [29] by parameterizingγ asγ = τ σ 2 n , where τ ∈ R + (typically τ = 5) and by modeling the error e(k) as a zero-mean Gaussian random variable with variance σ 2 n . From (16), one can observe that the probability of obtaining w(k + 1) 2 > w(k) 2 is small.…”
Section: Corollary 2 When An Update Occurs (Ie F (E(k)γ )mentioning
confidence: 99%
“…Moreover, a judicious choice of the error bound may not even assure optimal performance due to the nonstationarity of the underlying system. To overcome the error-bound estimation problem of the SM-NLMS algorithm [5], different solutions have been proposed in [6][7][8][9][10]. The error-bound estimation methods in [6][7][8][9] are not straightforward to apply to the SM-AP algorithm as they are application specific.…”
Section: Introductionmentioning
confidence: 99%