Tracking time-varying parameters with local regression

被引:21
|
作者
Joensen, A [1 ]
Madsen, H [1 ]
Nielsen, HA [1 ]
Nielsen, TS [1 ]
机构
[1] Tech Univ Denmark, Dept Math Modelling, DK-2800 Lyngby, Denmark
关键词
recursive estimation; varying-coefficient; conditional parametric; polynomial approximation; weighting functions;
D O I
10.1016/S0005-1098(00)00029-7
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper shows that the recursive least-squares (RLS) algorithm with forgetting factor is a special case of a varying-coefficient model, and a model which can easily be estimated via simple local regression. This observation allows us to formulate a new method which retains the RLS algorithm, but extends the algorithm by including polynomial approximations. Simulation results are provided, which indicates that this new method is superior to the classical RLS method, if the parameter variations are smooth. (C) 2000 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:1199 / 1204
页数:6
相关论文
共 50 条