A novel algorithm for feature selection using Harmony Search and its application for non-technical losses detection

Autor(es)

Ramos, Caio C. O. ^[1] ; Souza, Andre N. ^[2] ; Chiachia, Giovani ^[3] ; Falcao, Alexandre X. ^[3] ; Papa, Joao P. ^{[4, 5]}

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Dept Elect Engn, Polytech Sch, Sao Paulo - Brazil

^[2] UNESP Univ Estadual Paulista, Dept Elect Engn, Bauru - Brazil

^[3] Univ Estadual Campinas, Inst Comp, Campinas, SP - Brazil

^[4] UNESP Univ Estadual Paulista, Dept Comp, Bauru - Brazil

^[5] UNESP Univ Estadual Paulista, Dept Comp Sci, Bauru - Brazil

• Tipo de documento: Artigo Científico
• Fonte: COMPUTERS & ELECTRICAL ENGINEERING; v. 37, n. 6, p. 886-894, NOV 2011.
• Citações Web of Science: 47

Resumo

Finding an optimal subset of features that maximizes classification accuracy is still an open problem. In this paper, we exploit the speed of the Harmony Search algorithm and the Optimum-Path Forest classifier in order to propose a new fast and accurate approach for feature selection. Comparisons to some other pattern recognition and feature selection techniques showed that the proposed hybrid algorithm for feature selection outperformed them. The experiments were carried out in the context of identifying non-technical losses in power distribution systems. (C) 2011 Elsevier Ltd. All rights reserved. (AU)

• Processo FAPESP: 10/00994-8 - Aprendendo Representações Específicas para a Face de cada Pessoa
• Beneficiário: Giovani Chiachia
• Modalidade de apoio: Bolsas no Brasil - Doutorado