Circulant singular spectrum analysis: a new automated procedure for signal extraction
Identificadores
Enlace permanente (URI): http://hdl.handle.net/10017/45972DOI: 10.1016/j.sigpro.2020.107824
ISSN: 0165-1684
Fecha de publicación
2021Patrocinadores
MINECO/FEDER
Cita bibliográfica
Signal Processing, 2021, v. 179, n. 107824
Palabras clave
Circulant matrices
Principal components
Signal extraction
Singular spectrum analysis
Singular value decomposition
AM-FM Signals
Proyectos
nfo:eu-repo/grantAgreement/MINECO//ECO2015-70331-C2-1-R/ES/ANALISIS DE ACTIVIDAD ECONOMICA MEDIANTE INDICADORES Y EVALUACION DE POLITICAS PUBLICAS/
info:eu-repo/grantAgreement/MINECO//ECO2015-66593-P/ES/\"BIG DATA\" Y DATOS COMPLEJOS EN EMPRESA Y FINANZAS/
ECO2016-76818-C3-3-P
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-107161GB-C32/ES/INVESTIGACIONES EN TECNOLOGIA Y SOSTENIBILIDAD, INNOVACION Y EL MEDIOAMBIENTE/
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108079GB-C22/ES/NUEVOS METODOS ECONOMETRICOS PARA PREDICCION MACROECONOMICA Y ANALISIS DE POLITICAS ECONOMICAS/
Tipo de documento
info:eu-repo/semantics/article
Versión
info:eu-repo/semantics/publishedVersion
Versión del editor
www.elsevier.com/locate/sigproDerechos de acceso
info:eu-repo/semantics/openAccess
Resumen
Sometimes, it is of interest to single out the fluctuations associated to a given frequency. We propose a new variant of SSA, Circulant SSA (CiSSA), that allows to extract the signal associated to any frequency specified beforehand. This is a novelty when compared with other SSA procedures that need to iden- tify ex-post the frequencies associated to the extracted signals. We prove that CiSSA is asymptotically equivalent to these alternative procedures although with the advantage of avoiding the need of the subse- quent frequency identification. We check its good performance and compare it to alternative SSA methods through several simulations for linear and nonlinear time series. We also prove its validity in the nonsta- tionary case. We apply CiSSA in two different fields to show how it works with real data and find that it behaves successfully in both applications. Finally, we compare the performance of CiSSA with other state of the art techniques used for nonlinear and nonstationary signals with amplitude and frequency varying in time.
Ficheros en el ítem
Ficheros | Tamaño | Formato |
|
---|---|---|---|
circulant_senra_SP_2021.pdf | 4.230Mb |
|
Ficheros | Tamaño | Formato |
|
---|---|---|---|
circulant_senra_SP_2021.pdf | 4.230Mb |
|
Colecciones
- ECONOMÍA - Artículos [125]