Optimal arrangements of hyperplanes for SVM-based multiclass classification
Metadatos
Mostrar el registro completo del ítemEditorial
Springer
Fecha
2020-03Referencia bibliográfica
Published version: Advances in Data Analysis and Classification 14, p 175-199. https://doi.org/10.1007/s11634-019-00367-6
Patrocinador
MTM2016-74983-C2-1-R (MINECO, Spain); PP2016-PIP06 (Universidad de Granada); SEJ-534 (Junta de Andalucía)Resumen
In this paper, we present a novel SVM-based approach to construct multiclass classifiers by means of arrangements of hyperplanes. We propose different mixed integer (linear and non linear) programming formulations for the problem using extensions of widely used measures for misclassifying observations where the kernel trick can be adapted to be applicable. Some dimensionality reductions and variable fixing strategies are also developed for thesemodels. An extensive battery of experiments has been run which reveal the powerfulness of our proposal as compared with other previously proposed methodologies.