Identification of stable nonstationary lattice predictors by linear programming

Identification of stable nonstationary lattice predictors by linear programming

Time-varying models can be identified by lattice predictors with time-dependent reflection coefficients. The main defect of these predictors is that the magnitude of their coefficients cannot be controlled. In the present work a method is presented for removing such inconvenience based on linear pro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the IEEE 1986-05, Vol.74 (5), p.759-760
Hauptverfasser: Martinelli, G., Orlandi, G., Ricotti, L.P., Ragazzini, S.
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Circuit properties
Control systems
Electric, optical and optoelectronic circuits
Electronic circuits
Electronics
Equations
Exact sciences and technology
Lattices
Least squares approximation
Linear programming
Miscellaneous
Prediction algorithms
Predictive models
Reflection
Signal processing
Stability
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Time-varying models can be identified by lattice predictors with time-dependent reflection coefficients. The main defect of these predictors is that the magnitude of their coefficients cannot be controlled. In the present work a method is presented for removing such inconvenience based on linear programming.
ISSN:0018-9219
1558-2256
DOI:10.1109/PROC.1986.13543