Title :
LMS adaptation of an ARMAX model using the optimum scalar data nonlinearity algorithm
Author :
Hamerlain, Faiza
Author_Institution :
Lab. de Robotique et d´´Intelligence Artificielle, CDTA, Algiers, Algeria
Abstract :
The least mean square (LMS) adaptive filter can easily predict an ARMAX model. However, it is known that this filter coefficient converges quite slowly when the input signal is corrupted by white noise. Modified LMS algorithms, in which various quantities in the stochastic gradient estimate are operated upon by memoryless nonlinearities, have been shown to perform better than the LMS algorithm. Using a scalar data nonlinearity in stochastic gradient adaptation, as an equal-eigenvalue covariance structure for the data represents the best situation for stochastic gradient adaptation. Simulation results have clearly shown the significant performance improvement of the optimum scalar data nonlinearity algorithm for ARMAX model prediction in noise conditions
Keywords :
adaptive filters; autoregressive moving average processes; eigenvalues and eigenfunctions; least mean squares methods; stochastic processes; white noise; ARMAX model; ARMAX model prediction; LMS adaptation; equal-eigenvalue covariance structure; input signal corruption; least mean square adaptive filter; memoryless nonlinearities; noise conditions; optimum scalar data nonlinearity algorithm; scalar data nonlinearity; stochastic gradient adaptation; stochastic gradient estimate; white noise; Adaptive algorithm; Adaptive control; Adaptive filters; Convergence; Equations; Gaussian noise; Least squares approximation; Predictive models; Stochastic processes; Stochastic resonance;
Conference_Titel :
Industrial Electronics, 1999. ISIE '99. Proceedings of the IEEE International Symposium on
Conference_Location :
Bled
Print_ISBN :
0-7803-5662-4
DOI :
10.1109/ISIE.1999.796893
