Title :
An executable and asymptotically optimal adaptive RLS algorithm
Author :
Morimoto, Jiro ; Yamamoto, Yoshikazu ; Kobayashi, Ikunori ; Furumoto, Nariayo ; Tabuchi, Toshiaki
Author_Institution :
Fac. of Eng., Tokushima Bunri Univ., Kagawa, Japan
Abstract :
A setting method for the forgetting factor in recursive least squares (RLS) algorithms is presented. In a general adaptive setting method, to obtain the optimal value of the forgetting factor, the cost function constructed with the mean squared prediction errors is differentiated and the derivative that is set to zero is solved numerically. The problem of this method is that just one of local minimums is obtained unless the cost function is confirmed as unimodal. The main object of this contribution is to show the unimodality of the cost function of the RLS algorithm
Keywords :
adaptive estimation; least squares approximations; minimisation; recursive estimation; asymptotically optimal adaptive recursive least squares algorithm; cost function; forgetting factor; mean squared prediction errors; unimodality; Additive noise; Algorithm design and analysis; Cost function; Equations; Least squares approximation; Least squares methods; Linear regression; Resonance light scattering; Time varying systems; Vectors;
Conference_Titel :
SICE '97. Proceedings of the 36th SICE Annual Conference. International Session Papers
Conference_Location :
Tokushima
DOI :
10.1109/SICE.1997.625051
