• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Detecção de fraudes no consumo de energia elétrica usando árvores de decisão

MATOS, Yasmin Christine Correa 11 July 2017 (has links)
Submitted by Hellen Luz (hellencrisluz@gmail.com) on 2017-10-06T18:06:43Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_DeteccaoFraudesConsumo.pdf: 1616969 bytes, checksum: c2d6c39634607cb9195183bbcf50a032 (MD5) / Rejected by Irvana Coutinho (irvana@ufpa.br), reason: Aguardar as orientações on 2017-10-10T16:45:45Z (GMT) / Submitted by Hellen Luz (hellencrisluz@gmail.com) on 2017-10-11T16:28:39Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_DeteccaoFraudesConsumo.pdf: 1616969 bytes, checksum: c2d6c39634607cb9195183bbcf50a032 (MD5) / Approved for entry into archive by Irvana Coutinho (irvana@ufpa.br) on 2017-10-16T12:50:20Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_DeteccaoFraudesConsumo.pdf: 1616969 bytes, checksum: c2d6c39634607cb9195183bbcf50a032 (MD5) / Made available in DSpace on 2017-10-16T12:50:20Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_DeteccaoFraudesConsumo.pdf: 1616969 bytes, checksum: c2d6c39634607cb9195183bbcf50a032 (MD5) Previous issue date: 2017-07-11 / Os prejuízos causados nos últimos anos pelas perdas comerciais às concessionárias de distribuição de energia elétrica no Brasil têm sido estimados aproximadamente em R$ 7 bilhões. Essa realidade representa, um desafio para algumas das distribuidoras do país, as quais necessitam de medidas eficazes no combate às perdas comerciais. Neste cenário, a presente dissertação de mestrado, apresenta uma metodologia capaz de detectar fraudes no consumo de energia elétrica, usando uma técnica de mineração de dados, conhecida como árvore de decisão. Testes de desempenho do método foram realizados usando dados reais do histórico de consumo de energia elétrica e de fiscalização de irregularidades em unidades consumidoras (UC’s) da região metropolitana de Belém. Os resultados mostraram que o método proposto baseado em árvore de decisão possui bom desempenho na detecção de fraudes no consumo de energia elétrica. / In recent years, the injury caused by the nontechnical losses to power distribution utilities, in Brazil have been estimated at R$ 7 billion per year. This reality represents a challenge for some of country’s utilities, who need effective measures to combat commercial losses. In this scenario, this dissertation presents a methodology able of detecting fraud in the consumption of electric energy, using a technique of data mining, known as decision tree. Performance tests of the method were done using real data from the history of electricity consumption and the inspection of consumer units (CU’s) suspected of being irregular in the metropolitan region of Belém. The results showed that the proposed decision-tree based method performs well in the detection of fraud in the electric power consumption.

Page generated in 0.1014 seconds