| Grant number: | 12/14158-2 |
| Support Opportunities: | Regular Research Grants |
| Start date: | November 01, 2012 |
| End date: | December 31, 2014 |
| Field of knowledge: | Engineering - Electrical Engineering - Power Systems |
| Principal Investigator: | André Nunes de Souza |
| Grantee: | André Nunes de Souza |
| Host Institution: | Faculdade de Engenharia (FE). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil |
| Associated researchers: | João Paulo Papa |
Abstract
The identification of non-technical losses, also called commercial losses, has been of great importance in the last decade. By using datasets with hundreds of legal and illegal profiles, we can obtain a method to cluster data into subprofiles aiming to minimize the search for consumers that lead to a large amount of thefts, or even to classify all samples from such datasets in legal or illegal consumers. Equally important to the identification of such profiles, their characterization is also desirable in order to identify which features are really employed by artificial intelligence algorithms for the classification of such consumers as been legal or illegal. In this context, this research project aims the use of optimization techniques for feature selection and weighting to characterize the illegal consumers' profile, aiming to propose novel algorithms based on some evolutionary techniques recently presented in the literature, which have not been employed for such context up to date. (AU)
| Articles published in Agência FAPESP Newsletter about the research grant: |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |