Title :
Deconvolution/identification techniques for nonnegative signals
Author :
Goodman, Dennis M. ; Yu, David R.
Author_Institution :
Lawrence Livermore Nat. Lab., Livermore, CA, USA
Abstract :
Several methods for solving the nonparametric deconvolution/identification problem when the unknown is nonnegative are presented. The authors consider the constrained least squares method and discuss three ways to estimate the regularization parameter: the discrepancy principle, Mallow´s (1973) CL, and generalized cross validation. They consider maximum entropy methods. A new conjugate gradient algorithm and a preliminary comparison are presented
Keywords :
conjugate gradient methods; information theory; least squares approximations; signal processing; Mallow´s CL method; conjugate gradient algorithm; constrained least squares method; discrepancy principle; generalized cross validation; maximum entropy methods; nonnegative signals; nonparametric deconvolution/identification; regularization parameter estimation; Acoustic measurements; Deconvolution; Electromagnetic measurements; Equations; Frequency estimation; Gaussian noise; Laboratories; Least squares methods; Parameter estimation; Signal processing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226463
