What is the importance of selecting features for non-technical losses identification?
| Contribuinte(s) |
Universidade Estadual Paulista (UNESP) |
|---|---|
| Data(s) |
27/05/2014
27/05/2014
02/08/2011
|
| Resumo |
Although non-technical losses automatic identification has been massively studied, the problem of selecting the most representative features in order to boost the identification accuracy has not attracted much attention in this context. In this paper, we focus on this problem applying a novel feature selection algorithm based on Particle Swarm Optimization and Optimum-Path Forest. The results demonstrated that this method can improve the classification accuracy of possible frauds up to 49% in some datasets composed by industrial and commercial profiles. © 2011 IEEE. |
| Formato |
1045-1048 |
| Identificador |
http://dx.doi.org/10.1109/ISCAS.2011.5937748 Proceedings - IEEE International Symposium on Circuits and Systems, p. 1045-1048. 0271-4310 http://hdl.handle.net/11449/72586 10.1109/ISCAS.2011.5937748 2-s2.0-79960865826 |
| Idioma(s) |
eng |
| Relação |
Proceedings - IEEE International Symposium on Circuits and Systems |
| Direitos |
closedAccess |
| Palavras-Chave | #Automatic identification #Classification accuracy #Data sets #Feature selection algorithm #Identification accuracy #Non-technical loss #Automation #Classification (of information) #Particle swarm optimization (PSO) #Feature extraction |
| Tipo |
info:eu-repo/semantics/conferencePaper |
