A method of estimating time-varying spectra of nonstationary signals using recursive least squares (RLS) with variable forgetting factors (VFF's) is described. The VFF is adapted to a nonstationary signal by an extended prediction error criterion which accounts for the nonstationarity of the signal. This method has good adaptability in the nonstationary situation and low variance in the stationary situation. The feasibility of the approach is demonstrated with both simulation and experimental data.
机构:
Kings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Michigan State Univ, Dept Econ, E Lansing, MI 48825 USA
Rimini Ctr Econ Anal, Via Anghera 22, I-47921 Rimini, Emilia Romagna, ItalyKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Baillie, Richard T.
Calonaci, Fabio
论文数: 0引用数: 0
h-index: 0
机构:
Queen Mary Univ London, Sch Econom & Finance, London E1 4NS, EnglandKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Calonaci, Fabio
Kapetanios, George
论文数: 0引用数: 0
h-index: 0
机构:
Kings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, EnglandKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
机构:
Kings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Michigan State Univ, Dept Econ, E Lansing, MI 48825 USA
Rimini Ctr Econ Anal, Via Anghera 22, I-47921 Rimini, Emilia Romagna, ItalyKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Baillie, Richard T.
Calonaci, Fabio
论文数: 0引用数: 0
h-index: 0
机构:
Queen Mary Univ London, Sch Econom & Finance, London E1 4NS, EnglandKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England
Calonaci, Fabio
Kapetanios, George
论文数: 0引用数: 0
h-index: 0
机构:
Kings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, EnglandKings Coll London, Kings Business Sch, 30 Aldwych, London WC2B 4BG, England