Abstract | ||
---|---|---|
A new framework for designing robust adaptive filters is introduced. It is based on the optimization of a certain cost function subject to a time-dependent constraint on the norm of the filter update. Particularly, we present a robust variable step-size NLMS algorithm which optimizes the square of the a posteriori error. We also show the link between the proposed algorithm and another one derived using a robust statistics approach. In addition, a theoretical model for predicting the transient and steady-state behavior and a proof of almost sure filter convergence are provided. The algorithm is then tested in different environments for system identification and acoustic echo cancelation applications. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/TSP.2007.913142 | IEEE Transactions on Signal Processing |
Keywords | Field | DocType |
new robust variable step-size,certain cost function subject,robust adaptive filter,new framework,filter update,robust statistics approach,different environment,nlms algorithm,posteriori error,robust variable step-size nlms,proposed algorithm,cancelation application,probability density function,robust statistics,impulse noise,system testing,statistical analysis,noise,adaptive filters,adaptive filter,constraint optimization,cost function,steady state,indexing terms,convergence,statistics,robustness,adaptive filtering,predictive models | Mathematical optimization,Control theory,A priori and a posteriori,Algorithm,Robustness (computer science),Robust statistics,Adaptive filter,Robust control,System identification,Probability density function,Mathematics,Constrained optimization | Journal |
Volume | Issue | ISSN |
56 | 5 | 1053-587X |
Citations | PageRank | References |
68 | 2.99 | 14 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
L.R. Vega | 1 | 108 | 6.02 |
H. Rey | 2 | 274 | 18.90 |
Jacob Benesty | 3 | 1941 | 146.01 |
S. Tressens | 4 | 269 | 18.38 |