Demodulação M-QAM empregando técnicas de Aprendizado de Máquina
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações do Mackenzie |
Texto Completo: | https://dspace.mackenzie.br/handle/10899/28600 |
Resumo: | This work presents the challenges faced in the demodulation of uniform and non-uniform high-order M-QAM (Quadrature Amplitude Modulation) signals, using the LLR (LogLikelihood Ratio) technique, which is nowadays one of the most widely used in the modern communication systems. The main theoretical concepts are reviewed, such as, modulation, demodulation, machine learning and cognitive radio. Comparative results are presented for several machine learning algorithms, acting as classification and regression, until the definition by the final model that is compatible with the current standards. It is proposed a new method to demodulate the M-QAM signal, evaluating its response to different modulation orders and SNR (Signal-to-Noise Ratio) values, when concatenated to a channel encoder LDPC (Low-density Parity-Check). The experimental results demonstrate a performance gain of up to 1485% for 4096-QAM in comparison with the classical LLR Max-Log-MAP demodulator, keeping the same BER (Bit Error Rate) level. Finally, this new demodulator scheme was implemented in the environment of GRC (GNU Radio Companion) to validate computational simulations. |
id |
UPM_859e6f84859c31d5ff3d19a2fa99d457 |
---|---|
oai_identifier_str |
oai:dspace.mackenzie.br:10899/28600 |
network_acronym_str |
UPM |
network_name_str |
Biblioteca Digital de Teses e Dissertações do Mackenzie |
repository_id_str |
10277 |
spelling |
2021-12-18T21:44:19Z2021-12-18T21:44:19Z2020-08-17TOLEDO, Roberto Neves. Demodulação M-QAM empregando técnicas de Aprendizado de Máquina. 2020. 74 f. Dissertação (Engenharia Elétrica) - Universidade Presbiteriana Mackenzie, São Paulo, 2020https://dspace.mackenzie.br/handle/10899/28600This work presents the challenges faced in the demodulation of uniform and non-uniform high-order M-QAM (Quadrature Amplitude Modulation) signals, using the LLR (LogLikelihood Ratio) technique, which is nowadays one of the most widely used in the modern communication systems. The main theoretical concepts are reviewed, such as, modulation, demodulation, machine learning and cognitive radio. Comparative results are presented for several machine learning algorithms, acting as classification and regression, until the definition by the final model that is compatible with the current standards. It is proposed a new method to demodulate the M-QAM signal, evaluating its response to different modulation orders and SNR (Signal-to-Noise Ratio) values, when concatenated to a channel encoder LDPC (Low-density Parity-Check). The experimental results demonstrate a performance gain of up to 1485% for 4096-QAM in comparison with the classical LLR Max-Log-MAP demodulator, keeping the same BER (Bit Error Rate) level. Finally, this new demodulator scheme was implemented in the environment of GRC (GNU Radio Companion) to validate computational simulations.Este trabalho apresenta os desafios enfrentados na demodulação de sinais M-QAM (Quadrature Amplitude Modulation) de alta ordem, uniformes e não uniformes, com o método de LLR (Log-Likelihood Ratio), que é um dos mais utilizadas nos sistemas de comunicação modernos. São abordados os principais conceitos téoricos como modulação, demodulação, aprendizado de máquina e rádio cognitivo. Resultados comparativos são apresentados para diversos algoritmos de aprendizado de máquina, atuando como classificação e regressão, até a definição pelo modelo final que é compatível com os padrões atuais. Então, é proposto um novo modelo de demodulação do sinal M-QAM, avaliando sua resposta para diferentes ordens de modulação e valores de SNR (Signal-to-Noise Ratio), quando concatenado a um codificador de canal LDPC (Low-density Parity-Check). Os resultados experimentais demonstram um ganho de desempenho de até 1485% para 4096-QAM em comparação com o demodulador clássico LLR Max-Log-MAP, mantendo o mesmo patamar de BER (Bit Error Rate). Finalmente, esse novo esquema demodulador foi implementado no ambiente do GRC (GNU Radio Companion) para validar as simulações computacionais.Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorFundo Mackenzie de Pesquisaapplication/pdfporUniversidade Presbiteriana MackenzieEngenharia ElétricaUPMBrasilEscola de Engenharia Mackenzie (EE)http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessaprendizado de máquinademodulaçãoLLR, M-QAMCNPQ::ENGENHARIASDemodulação M-QAM empregando técnicas de Aprendizado de Máquinainfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisSilva, Leandro Augusto dahttp://lattes.cnpq.br/1396385111251741 / https://orcid.org/0000-0002-8671-3102Akamine, Cristianohttp://lattes.cnpq.br/0394598624993168 / https://orcid.org/0000-0002-3161-4668Menezes, Mario Olimpio dehttp://lattes.cnpq.br/4882949829423994 / https://orcid.org/0000-0003-0263-3541Lima, Eduardo Rodrigues dehttp://lattes.cnpq.br/1801783933113600http://lattes.cnpq.br/6519617116139637 / https://orcid.org/0000-0003-2038-4120Toledo, Roberto NevesdemodulationLLRmachine learningM-QAMreponame:Biblioteca Digital de Teses e Dissertações do Mackenzieinstname:Universidade Presbiteriana Mackenzie (MACKENZIE)instacron:MACKENZIEORIGINALROBERTO NEVES TOLEDO -protegido.pdfRoberto Neves Toledoapplication/pdf3065427https://dspace.mackenzie.br/bitstream/10899/28600/1/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf09b5e171cebcf32acb8612d1d1d58c7fMD51CC-LICENSElicense_urlapplication/octet-stream49https://dspace.mackenzie.br/bitstream/10899/28600/2/license_url4afdbb8c545fd630ea7db775da747b2fMD52license_textapplication/octet-stream0https://dspace.mackenzie.br/bitstream/10899/28600/3/license_textd41d8cd98f00b204e9800998ecf8427eMD53license_rdfapplication/octet-stream0https://dspace.mackenzie.br/bitstream/10899/28600/4/license_rdfd41d8cd98f00b204e9800998ecf8427eMD54LICENSElicense.txttext/plain2108https://dspace.mackenzie.br/bitstream/10899/28600/5/license.txt1ca4f25d161e955cf4b7a4aa65b8e96eMD55TEXTROBERTO NEVES TOLEDO -protegido.pdf.txtROBERTO NEVES TOLEDO -protegido.pdf.txtExtracted texttext/plain94030https://dspace.mackenzie.br/bitstream/10899/28600/6/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf.txtdf1cb141fac373ab4a383d297a20f545MD56THUMBNAILROBERTO NEVES TOLEDO -protegido.pdf.jpgROBERTO NEVES TOLEDO -protegido.pdf.jpgGenerated Thumbnailimage/jpeg1243https://dspace.mackenzie.br/bitstream/10899/28600/7/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf.jpg721347f3cbc2bd631991f2a002f0afa7MD5710899/286002021-12-19 03:02:31.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Biblioteca Digital de Teses e Dissertaçõeshttp://tede.mackenzie.br/jspui/PRI |
dc.title.por.fl_str_mv |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
title |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
spellingShingle |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina Toledo, Roberto Neves aprendizado de máquina demodulação LLR, M-QAM CNPQ::ENGENHARIAS |
title_short |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
title_full |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
title_fullStr |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
title_full_unstemmed |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
title_sort |
Demodulação M-QAM empregando técnicas de Aprendizado de Máquina |
author |
Toledo, Roberto Neves |
author_facet |
Toledo, Roberto Neves |
author_role |
author |
dc.contributor.advisor-co1.fl_str_mv |
Silva, Leandro Augusto da |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://lattes.cnpq.br/1396385111251741 / https://orcid.org/0000-0002-8671-3102 |
dc.contributor.advisor1.fl_str_mv |
Akamine, Cristiano |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/0394598624993168 / https://orcid.org/0000-0002-3161-4668 |
dc.contributor.referee1.fl_str_mv |
Menezes, Mario Olimpio de |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/4882949829423994 / https://orcid.org/0000-0003-0263-3541 |
dc.contributor.referee2.fl_str_mv |
Lima, Eduardo Rodrigues de |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/1801783933113600 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/6519617116139637 / https://orcid.org/0000-0003-2038-4120 |
dc.contributor.author.fl_str_mv |
Toledo, Roberto Neves |
contributor_str_mv |
Silva, Leandro Augusto da Akamine, Cristiano Menezes, Mario Olimpio de Lima, Eduardo Rodrigues de |
dc.subject.por.fl_str_mv |
aprendizado de máquina demodulação LLR, M-QAM |
topic |
aprendizado de máquina demodulação LLR, M-QAM CNPQ::ENGENHARIAS |
dc.subject.cnpq.fl_str_mv |
CNPQ::ENGENHARIAS |
description |
This work presents the challenges faced in the demodulation of uniform and non-uniform high-order M-QAM (Quadrature Amplitude Modulation) signals, using the LLR (LogLikelihood Ratio) technique, which is nowadays one of the most widely used in the modern communication systems. The main theoretical concepts are reviewed, such as, modulation, demodulation, machine learning and cognitive radio. Comparative results are presented for several machine learning algorithms, acting as classification and regression, until the definition by the final model that is compatible with the current standards. It is proposed a new method to demodulate the M-QAM signal, evaluating its response to different modulation orders and SNR (Signal-to-Noise Ratio) values, when concatenated to a channel encoder LDPC (Low-density Parity-Check). The experimental results demonstrate a performance gain of up to 1485% for 4096-QAM in comparison with the classical LLR Max-Log-MAP demodulator, keeping the same BER (Bit Error Rate) level. Finally, this new demodulator scheme was implemented in the environment of GRC (GNU Radio Companion) to validate computational simulations. |
publishDate |
2020 |
dc.date.issued.fl_str_mv |
2020-08-17 |
dc.date.accessioned.fl_str_mv |
2021-12-18T21:44:19Z |
dc.date.available.fl_str_mv |
2021-12-18T21:44:19Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
TOLEDO, Roberto Neves. Demodulação M-QAM empregando técnicas de Aprendizado de Máquina. 2020. 74 f. Dissertação (Engenharia Elétrica) - Universidade Presbiteriana Mackenzie, São Paulo, 2020 |
dc.identifier.uri.fl_str_mv |
https://dspace.mackenzie.br/handle/10899/28600 |
identifier_str_mv |
TOLEDO, Roberto Neves. Demodulação M-QAM empregando técnicas de Aprendizado de Máquina. 2020. 74 f. Dissertação (Engenharia Elétrica) - Universidade Presbiteriana Mackenzie, São Paulo, 2020 |
url |
https://dspace.mackenzie.br/handle/10899/28600 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Presbiteriana Mackenzie |
dc.publisher.program.fl_str_mv |
Engenharia Elétrica |
dc.publisher.initials.fl_str_mv |
UPM |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Escola de Engenharia Mackenzie (EE) |
publisher.none.fl_str_mv |
Universidade Presbiteriana Mackenzie |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações do Mackenzie instname:Universidade Presbiteriana Mackenzie (MACKENZIE) instacron:MACKENZIE |
instname_str |
Universidade Presbiteriana Mackenzie (MACKENZIE) |
instacron_str |
MACKENZIE |
institution |
MACKENZIE |
reponame_str |
Biblioteca Digital de Teses e Dissertações do Mackenzie |
collection |
Biblioteca Digital de Teses e Dissertações do Mackenzie |
bitstream.url.fl_str_mv |
https://dspace.mackenzie.br/bitstream/10899/28600/1/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf https://dspace.mackenzie.br/bitstream/10899/28600/2/license_url https://dspace.mackenzie.br/bitstream/10899/28600/3/license_text https://dspace.mackenzie.br/bitstream/10899/28600/4/license_rdf https://dspace.mackenzie.br/bitstream/10899/28600/5/license.txt https://dspace.mackenzie.br/bitstream/10899/28600/6/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf.txt https://dspace.mackenzie.br/bitstream/10899/28600/7/ROBERTO%20NEVES%20TOLEDO%20-protegido.pdf.jpg |
bitstream.checksum.fl_str_mv |
09b5e171cebcf32acb8612d1d1d58c7f 4afdbb8c545fd630ea7db775da747b2f d41d8cd98f00b204e9800998ecf8427e d41d8cd98f00b204e9800998ecf8427e 1ca4f25d161e955cf4b7a4aa65b8e96e df1cb141fac373ab4a383d297a20f545 721347f3cbc2bd631991f2a002f0afa7 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
|
repository.mail.fl_str_mv |
|
_version_ |
1757177228648513536 |