<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPEW34M/45DJ23H</identifier>
		<repository>sid.inpe.br/sibgrapi/2021/09.10.14.22</repository>
		<lastupdate>2021:09.10.14.22.17 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2021/09.10.14.22.17</metadatarepository>
		<metadatalastupdate>2022:09.10.00.16.17 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2021}</metadatalastupdate>
		<citationkey>RochaVPBAMSRSMN:2021:CoStMe</citationkey>
		<title>A Comparative Study of Methods based on Deep Neural Networks for Self-reading of Energy Consumption in a Chatbot Application Context</title>
		<format>On-line</format>
		<year>2021</year>
		<numberoffiles>1</numberoffiles>
		<size>877 KiB</size>
		<author>Rocha, Carlos Vinicios Martins,</author>
		<author>Vieira, Pedro Henrique Carvalho,</author>
		<author>Pinto, Antonio Moreira,</author>
		<author>Bernhard, Pedro Vinnicius,</author>
		<author>Anchieta Junior, Ricardo José Fernandes,</author>
		<author>Marques, Ricardo Costa da Silva,</author>
		<author>Silva, Italo Francyles Santos da,</author>
		<author>Rocha, Simara Vieira da,</author>
		<author>Silva, Aristófanes Corrêa,</author>
		<author>Monteiro, Eliana Márcia Garros,</author>
		<author>Nogueira, Hugo Daniel Castro Silva,</author>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Federal University of Maranhão</affiliation>
		<affiliation>Equatorial Energy Group</affiliation>
		<affiliation>Equatorial Energy Group</affiliation>
		<editor>Paiva, Afonso,</editor>
		<editor>Menotti, David,</editor>
		<editor>Baranoski, Gladimir V. G.,</editor>
		<editor>Proença, Hugo Pedro,</editor>
		<editor>Junior, Antonio Lopes Apolinario,</editor>
		<editor>Papa, João Paulo,</editor>
		<editor>Pagliosa, Paulo,</editor>
		<editor>dos Santos, Thiago Oliveira,</editor>
		<editor>e Sá, Asla Medeiros,</editor>
		<editor>da Silveira, Thiago Lopes Trugillo,</editor>
		<editor>Brazil, Emilio Vital,</editor>
		<editor>Ponti, Moacir A.,</editor>
		<editor>Fernandes, Leandro A. F.,</editor>
		<editor>Avila, Sandra,</editor>
		<e-mailaddress>francyles@nca.ufma.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)</conferencename>
		<conferencelocation>Gramado, RS, Brazil (virtual)</conferencelocation>
		<date>18-22 Oct. 2021</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Industry Application Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<keywords>self-reading, energy consumption, chatbot application, image processing, deep learning.</keywords>
		<abstract>Self-reading is a process in which the consumer is responsible for measuring his own energy consumption, which can be done through digital platforms, such as websites or mobile applications. The Equatorial Energy group's electric utilities have been working on developing a chatbot application through which consumers can send an image of their energy meter to a server that runs a method based on image processing and deep learning for the automatic recognition of consumption reading. However, the incorporation of these methods in a solution available to the public should consider factors such as response time and accuracy, so that it presents a satisfactory response time when it needs to handle a large number of simultaneous requests. Therefore, this paper presents a comparative study between approaches developed for the automatic recognition of consumption readings in images of electric meters sent to the server. Response time performances are analyzed through stress tests that simulate the real application scenario. The mean average precision (mAP) and the accuracy metrics of the methods are also analyzed in order to evaluate the generalization of the used convolutional neural networks.</abstract>
		<language>en</language>
		<targetfile>Autoclara___Sibgrapi_2021___English__sem_subpastas_.pdf</targetfile>
		<usergroup>francyles@nca.ufma.br</usergroup>
		<visibility>shown</visibility>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPEW34M/45PQ3RS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2021/11.12.11.46 5</citingitemlist>
		<citingitemlist>sid.inpe.br/banon/2001/03.30.15.38.24 2</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2021/09.10.14.22</url>
	</metadata>
</metadatalist>