Title :
A quadratic adaptive recursive filter
Author :
Canales, Timothy J. ; Etter, Delores M.
Author_Institution :
Gultron Data Syst., Albuquerque, NM, USA
Abstract :
An adaptive recursive filter is developed which exhibits quadratic performance properties. The development is based upon the concept of base operators which form a basis for the construction of the new recursive filter operator. A stochastic gradient algorithm is proposed and demonstrated. The filter is stable under adaptation and reliably converges, because the performance function is unimodal. The simplicity of the nonrecursive LMS (least-mean-square) algorithm is preserved
Keywords :
adaptive filters; convergence; filtering and prediction theory; stochastic processes; base operators; quadratic adaptive recursive filter; quadratic performance properties; stochastic gradient algorithm; Adaptive algorithm; Adaptive filters; Data systems; Filtering algorithms; Irrigation; Least squares approximation; Marine vehicles; Nonlinear filters; Stability; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112378
