Title :
Algorithms for improved performance in adaptive polynomial filters with Gaussian input signals
Author :
Li, Xiaohui ; Jenkins, W. Kenneth ; Therrien, Charles W.
Author_Institution :
Coordinated Sci. Lab., Illinois Univ., Urbana, IL, USA
Abstract :
The structure of the input covariance matrix in Volterra second order adaptive filters for general colored Gaussian input processes is analyzed to determine how to best formulate a computationally efficient fast adaptive algorithm. It is shown that when the input signal samples are ordered properly within the input data vector, the covariance matrix inherits a block diagonal structure, with some of the sub-blocks also having a diagonal structure. Some new results in developing and evaluating computationally efficient quasi-Newton adaptive algorithms are presented that take advantage of the sparsity and unique structure of the covariance matrix that results from this formulation.
Keywords :
Gaussian processes; Newton method; Volterra series; adaptive filters; adaptive signal processing; covariance matrices; filtering theory; signal sampling; Gaussian input signals; Volterra second order adaptive filters; Volterra series; adaptive polynomial filters; block diagonal structure; colored Gaussian input processes; computational complexity; fast adaptive algorithm; input covariance matrix; input data vector; input signal samples; quasiNewton adaptive algorithms; Adaptive algorithm; Adaptive filters; Covariance matrix; Equations; Filtering algorithms; Least squares approximation; Nonlinear filters; Polynomials; Signal processing algorithms; Vectors;
Conference_Titel :
Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-8186-7646-9
DOI :
10.1109/ACSSC.1996.600870