Multi-labeler classification using kernel representations and mixture of classifiers
Date
2017Author
Imbajoa-Ruiz D.E.
Gustin I.D.
Bolaños-Ledezma M.
Arciniegas-Mejía A.F.
Guasmayan-Guasmayan F.A.
Bravo-Montenegro M.J.
Castro-Ospina A.E.
Peluffo-Ordóñez D.H.
Metadata
Show full item recordAbstract
This work introduces a multi-labeler kernel novel approach for data classification learning from multiple labelers. The learning process is done by training support-vector machine classifiers using the set of labelers (one labeler per classifier). The objective functions representing the boundary decision of each classifier are mixed by means of a linear combination. Followed from a variable relevance, the weighting factors are calculated regarding kernel matrices representing each labeler. To do so, a so-called supervised kernel function is also introduced, which is used to construct kernel matrices. Our multi-labeler method reaches very good results being a suitable alternative to conventional approaches. © Springer International Publishing AG 2017.
Collections
- Artículos Scopus [165]
Description
UNIVERSIDAD MARIANA
- Calle 18 No. 34-104 Pasto (N)
- (057) + 7244460 - Cel 3127306850
- informacion@umariana.edu.co
- NIT: 800092198-5
- Código SNIES: 1720
- Res. 1362 del 3 de febrero de 1983
NORMATIVIDAD INSTITUCIONAL
PROGRAMAS DE ESTUDIO
Para la recepción de notificaciones judiciales se encuentra habilitada la cuenta de correo electronico notificacionesjudiciales@umariana.edu.co
CONVOCATORIASINSCRIPCIÓN DE HOJAS DE VIDAGESTIÓN DEL TALENTO HUMANO
POLÍTICA DE PROTECCIÓN DE DATOS PERSONALESCONDICIONES DE USO U TÉRMINOS LEGALESRÉGIMEN TRIBUTARIO ESPECIAL 2021

Copyright Universidad Mariana
Tecnología implementada por