Title :
FIR system identification using higher order statistics alone
Author :
Zhang, Xian-Da ; Zhang, Yuan-Sheng
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
fDate :
10/1/1994 12:00:00 AM
Abstract :
This paper focuses on FIR system identification in Gaussian ARMA noise using higher order cumulants alone. Two new types of cumulant-based normal equations are established, and two algorithms are proposed for MA parameter estimation. Simulations verify the high performance of the new developments
Keywords :
digital filters; filtering and prediction theory; identification; parameter estimation; statistical analysis; stochastic processes; FIR system identification; Gaussian ARMA noise; MA parameter estimation; algorithms; cumulant-based normal equations; higher order cumulants; higher order statistics; simulations; Additive noise; Equations; Finite impulse response filter; Gaussian noise; Higher order statistics; Linear algebra; Optimization methods; Parameter estimation; Signal processing; System identification;
Journal_Title :
Signal Processing, IEEE Transactions on
