Back to results
US 2004/0071207 A1Published application
Adaptive filter
AssigneeQinetiq Limited
InventorsIan David Skidmore, Ian Keith Proulder
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeQinetiq Limited
InventorsIan David Skidmore, Ian Keith Proulder
Estimating the term…
An adaptive filter is implemented by a computer (10) processing an input signal using a recursive least squares lattice (RLSL) algorithm (12) to obtain forward and backward least squares prediction residuals. A prediction residual is the difference between a data element in a sequence of elements and a prediction of that element from other sequence elements. Forward and backward residuals are converted at (14) to interpolation residuals which are unnormalised Kalman gain vector coefficients. Interpolation residuals are normalised to produce the Kalman gain vector at (16). The Kalman gain vector is combined at (18) with input and reference signals x(t) and y(t), which provides updates for the filter coefficients or weights to reflect these signals as required to provide adaptive filtering.
An adaptive filter characterised in that it is arranged to update filter weights by means of a gain vector derived from interpolation residuals of a sequence of signal samples applied to the filter.
An adaptive filter characterised in that it is arranged to:
An adaptive filter according to claim. 10 characterised in that iteration in a sequence to generate an un-normalised element of the gain vector begins with use of one of two residuals immediately adjacent and on opposite sides of a halfway point, the residual of use being that having a relatively higher value of an index not to be altered in the iteration sequence, and the relevant halfway point being halfway between two quantities:
A method for adaptive filtering characterised in that it includes updating filter weights with a gain vector derived from interpolation residuals of a sequence of signal samples provided as data for filtering.
A method for adaptive filtering characterised in that it includes:
A method according to claim 17 or 18 characterised in that it is arranged to obtain prediction residuals by processing a sequence of signal samples using a recursive least squares lattice (RLSL) algorithm.
A computer program for implementing an adaptive filter characterised in that it is arranged to generate updated filter weights by means of a gain vector derived from interpolation residuals of a sequence of signal samples provided as data for filtering.
A computer program for implementing an adaptive filter characterised in that it is arranged to:
Dependencies are inferred from the claim text.