Universal and automatic elbow detection for learning the effective number of components in model selection problems
dc.contributor.author | Morgado, Eduardo | |
dc.contributor.author | Martino, Luca | |
dc.contributor.author | San Millán-Castillo, Roberto | |
dc.date.accessioned | 2024-01-23T08:58:41Z | |
dc.date.available | 2024-01-23T08:58:41Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | Morgado, E., Martino, L., & San Millán-Castillo, R. (2023). Universal and automatic elbow detection for learning the effective number of components in model selection problems. Digital Signal Processing, 104103. | es |
dc.identifier.issn | 0165-1684 | |
dc.identifier.uri | https://hdl.handle.net/10115/28705 | |
dc.description.abstract | We design a Universal Automatic Elbow Detector (UAED) for deciding the effective number of components in model selection problems. The relationship with the information criteria widely employed in the literature is also discussed. The proposed UAED does not require the knowledge of a likelihood function and can be easily applied in diverse applications, such as regression and classification, feature and/or order selection, clustering, and dimension reduction. Several experiments involving synthetic and real data show the advantages of the proposed scheme with benchmark techniques in the literature. | es |
dc.language.iso | eng | es |
dc.publisher | Elsevier | es |
dc.subject | Model selection | es |
dc.subject | Order selection | es |
dc.subject | Automatic elbow detection | es |
dc.subject | Variable selection | es |
dc.subject | Clustering | es |
dc.title | Universal and automatic elbow detection for learning the effective number of components in model selection problems | es |
dc.type | info:eu-repo/semantics/article | es |
dc.identifier.doi | 10.1016/j.dsp.2023.104103 | es |
dc.rights.accessRights | info:eu-repo/semantics/embargoedAccess | es |
Files in this item
This item appears in the following Collection(s)
-
Artículos de Revista [3706]
Los ítems de digital-BURJC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario