A class of order statistic LMS algorithms
- 1 January 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 40 (1) , 44-53
- https://doi.org/10.1109/78.157180
Abstract
Conventional gradient-based adaptive filters, as typified by the well-known LMS algorithm, use an instantaneous estimate of the error-surface gradient to update the filter coefficients. Such a strategy leaves the algorithm extremely vulnerable to impulsive interference. A class of adaptive algorithms employing order statistic filtering of the sampled gradient estimates is presented. These algorithms, dubbed order statistic least mean squares (OSLMS), are designed to facilitate adaptive filter performance close to the least squares optimum across a wide range of input environments from Gaussian to highly impulsive. Three specific OSLMS filters are defined: the median LMS, the average LMS, and the trimmed-mean LMS. The properties of these algorithms are investigated and the potential for improvement demonstrated. Finally, a general adaptive OSLMS scheme in which the nature of the order-statistic operator is also adapted in response to the statistics of the input signal is presented. It is shown that this can facilitate performance gains over a wide range of input data types.Keywords
This publication has 20 references indexed in Scilit:
- A class of nonlinear adaptive filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Median LMS algorithmElectronics Letters, 1989
- An algorithm and a pipelined architecture for order-statistic determination and L-filteringIEEE Transactions on Circuits and Systems, 1989
- Application of two-dimensional generalized mean filtering for removal of impulse noises from imagesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- Alpha-trimmed means and their relationship to median filtersIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- A generalization of median filtering using linear combinations of order statisticsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1983
- Time delay estimation using the LMS adaptive filter--Static behaviorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Adaptive noise canceling for speech signalsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978
- More Light on the Kurtosis and Related StatisticsJournal of the American Statistical Association, 1972
- Some Observations on Robust EstimationJournal of the American Statistical Association, 1967