Multiobjective Optimization of Classifiers by Means of 3-D Convex Hull Based Evolutionary Algorithm

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@Misc{oai:arXiv.org:1412.5710,

• title = "Multiobjective Optimization of Classifiers by Means of {3-D} Convex Hull Based Evolutionary Algorithm",
• note = "Comment: 32 pages, 26 figures",
• author = "Jiaqi Zhao and Vitor Basto Fernandes and Licheng Jiao and Iryna Yevseyeva and Asep Maulana and Rui Li and Thomas Baeck and Michael T. M. Emmerich",
• year = "2014",
• month = dec # "~17",
• bibsource = "OAI-PMH server at export.arxiv.org",
• oai = "oai:arXiv.org:1412.5710",
• keywords = "genetic algorithms, genetic programming",
• URL = "http://arxiv.org/abs/1412.5710",
• abstract = "Finding a good classifier is a multiobjective optimisation problem with different error rates and the costs to be minimised. The receiver operating characteristic is widely used in the machine learning community to analyse the performance of parametric classifiers or sets of Pareto optimal classifiers. In order to directly compare two sets of classifiers the area (or volume) under the convex hull can be used as a scalar indicator for the performance of a set of classifiers in receiver operating characteristic space. Recently, the convex hull based multiobjective genetic programming algorithm was proposed and successfully applied to maximise the convex hull area for binary classification problems. The contribution of this paper is to extend this algorithm for dealing with higher dimensional problem formulations. In particular, we discuss problems where parsimony (or classifier complexity) is stated as a third objective and multi-class classification with three different true classification rates to be maximised. The design of the algorithm proposed in this paper is inspired by indicator-based evolutionary algorithms, where first a performance indicator for a solution set is established and then a selection operator is designed that complies with the performance indicator. In this case, the performance indicator will be the volume under the convex hull. The algorithm is tested and analysed in a proof of concept study on different benchmarks that are designed for measuring its capability to capture relevant parts of a convex hull. Further benchmark and application studies on email classification and feature selection round up the analysis and assess robustness and usefulness of the new algorithm in real world settings.",
• notes = "see \cite{Zhao:2016:IS}",

}

Genetic Programming entries for Jiaqi Zhao Vitor Basto-Fernandes Licheng Jiao Iryna Yevseyeva Asep Maulana Rui Li Thomas Back Michael Emmerich

Citations