Multiobjective optimization of classifiers by means of 3-D convex Hull based evolutionary algorithms

The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves are frequently used in the machine learning community to analyze the performance of binary classifiers. Recently, the convex-hull-based multiobjective genetic programming algorithm was proposed and successfully app...

ver descrição completa

Detalhes bibliográficos
Autor principal: Zhao, J. (author)
Outros Autores: Basto-Fernandes, V. (author), Jiao, L. (author), Yevseyeva, I. (author), Maulana, A. (author), Li, R. (author), Bäck, T. (author), Tang, K. (author), Emmerichd, M. T. M. (author)
Formato: article
Idioma:eng
Publicado em: 2017
Assuntos:
Convex hull
Classification
Evolutionary multiobjective optimization
Parsimony
ROC analysis
Anti-spam filters
Texto completo:http://hdl.handle.net/10071/12775
País:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/12775

Texto Completo

http://hdl.handle.net/10071/12775

Registos relacionados