Quantum neurons with real weights for diabetes prediction
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFPE |
Texto Completo: | https://repositorio.ufpe.br/handle/123456789/42831 |
Resumo: | Parametric models with real numbers valued parameters have greater performance than its counterparts with binary valued weights, due to the gain in representing informa- tion with real values, and therefore having a larger space for memory association. In this work, is proposed a quantum neuron capable of store real weights and preserve the gain of the superposition property, encoding the information in the probability amplitudes of the quantum system, the Real Weights Quantum Neuron. Its performance is compared with other quantum neurons to analyze the application of the quantum neurons on real-world problems, i.e diabetes classification. The results of the experiments shows that a single quantum neuron is capable of achieving an accuracy rate of 100% in the XOR problem and an accuracy rate of 100% in a non-linear dataset, demonstrating that the quantum neurons with real weights are capable of modeling non-linearly separable problems. In the problem of diagnosing diabetes, quantum neurons achieved an accuracy rate of 76% and AUC-ROC of 88%, while its classic version, the perceptron, reached only 63% accuracy and the artificial neural network reached 80% AUC-ROC. These results indicate that a single quantum neuron performs better than its classical version and even the artificial neural network for AUC-ROC, demonstrating potential for use in healthcare applications in the near future. This work is also a contribution to the field of quantum neural networks, which can be further advanced from the quantum neuron proposed. |
id |
UFPE_f1d2f06765689eaaa3842678c86e5f73 |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/42831 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
2221 |
spelling |
MONTEIRO, Cláudio Luis Alveshttp://lattes.cnpq.br/2883009157618518http://lattes.cnpq.br/9643216021359436PAULA NETO, Fernando Maciano de2022-02-14T13:31:00Z2022-02-14T13:31:00Z2021-09-02MONTEIRO, Cláudio Luis Alves. Quantum neurons with real weights for diabetes prediction. 2021. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Pernambuco, Recife, 2021.https://repositorio.ufpe.br/handle/123456789/42831Parametric models with real numbers valued parameters have greater performance than its counterparts with binary valued weights, due to the gain in representing informa- tion with real values, and therefore having a larger space for memory association. In this work, is proposed a quantum neuron capable of store real weights and preserve the gain of the superposition property, encoding the information in the probability amplitudes of the quantum system, the Real Weights Quantum Neuron. Its performance is compared with other quantum neurons to analyze the application of the quantum neurons on real-world problems, i.e diabetes classification. The results of the experiments shows that a single quantum neuron is capable of achieving an accuracy rate of 100% in the XOR problem and an accuracy rate of 100% in a non-linear dataset, demonstrating that the quantum neurons with real weights are capable of modeling non-linearly separable problems. In the problem of diagnosing diabetes, quantum neurons achieved an accuracy rate of 76% and AUC-ROC of 88%, while its classic version, the perceptron, reached only 63% accuracy and the artificial neural network reached 80% AUC-ROC. These results indicate that a single quantum neuron performs better than its classical version and even the artificial neural network for AUC-ROC, demonstrating potential for use in healthcare applications in the near future. This work is also a contribution to the field of quantum neural networks, which can be further advanced from the quantum neuron proposed.CAPESEste trabalho apresenta resultados sobre a aplicação de algoritmos de aprendizagem de máquina quântica no setor de saúde. Foi desenvolvida e testada uma proposta de neurônio quântico capaz de armazenar pesos reais em comparação com outros neurônios quânticos. Esse modelos podem transportar uma quantidade exponencial de informação para um número linear de unidades de informação quântica (qubits) usando a propriedade quântica de superposição. Foi comparado o desempenho desses algoritmos nos seguintes problemas: simular o operador XOR, resolver um problema não linear genérico e pre- visão de diabetes em pacientes. Os resultados dos experimentos mostraram que um único neurônio quântico é capaz de atingir uma acurácia de 100% no problema XOR e 100% de acurácia em um conjunto de dados não linear, demonstrando que neurônios quânti- cos com pesos reais são capazes de classificar corretamente problemas não linearmente separáveis. No problema de classificação de diabetes, os neurônios quânticos alcançaram uma acurácia de 76% e AUC-ROC de 88%, enquanto sua versão clássica, o perceptron, atingiu apenas 63% de acurácia e a rede neural artifical atingiu 80% AUC-ROC. Esses resultados indicam que um único neurônio quântico tem um desempenho maior que sua versão clássica e até mesmo que a rede neural artifical na AUC-ROC, demonstrando seu potencial para uso em aplicações para o setor de saúde. Este trabalho é também uma contribuição ao campo das redes neurais quânticas, que pode ser avançada a partir do neurônio quântico proposto.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilInteligência computacionalAprendizado de máquinaQuantum neurons with real weights for diabetes predictioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesismestradoinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEORIGINALDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdfDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdfapplication/pdf1837135https://repositorio.ufpe.br/bitstream/123456789/42831/1/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdfabc7f380871baaefd2fcce825f98c0fdMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-82142https://repositorio.ufpe.br/bitstream/123456789/42831/2/license.txt6928b9260b07fb2755249a5ca9903395MD52TEXTDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdf.txtDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdf.txtExtracted texttext/plain101877https://repositorio.ufpe.br/bitstream/123456789/42831/3/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdf.txte3658ba6ea344804da6fbaa872399e68MD53THUMBNAILDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdf.jpgDISSERTAÇÃO Cláudio Luis Alves Monteiro.pdf.jpgGenerated Thumbnailimage/jpeg1250https://repositorio.ufpe.br/bitstream/123456789/42831/4/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdf.jpg6d7d26ef4212c5dd0ae7766dc6396ab9MD54123456789/428312022-02-15 02:14:59.357oai:repositorio.ufpe.br:123456789/42831VGVybW8gZGUgRGVww7NzaXRvIExlZ2FsIGUgQXV0b3JpemHDp8OjbyBwYXJhIFB1YmxpY2HDp8OjbyBkZSBEb2N1bWVudG9zIG5vIFJlcG9zaXTDs3JpbyBEaWdpdGFsIGRhIFVGUEUKIAoKRGVjbGFybyBlc3RhciBjaWVudGUgZGUgcXVlIGVzdGUgVGVybW8gZGUgRGVww7NzaXRvIExlZ2FsIGUgQXV0b3JpemHDp8OjbyB0ZW0gbyBvYmpldGl2byBkZSBkaXZ1bGdhw6fDo28gZG9zIGRvY3VtZW50b3MgZGVwb3NpdGFkb3Mgbm8gUmVwb3NpdMOzcmlvIERpZ2l0YWwgZGEgVUZQRSBlIGRlY2xhcm8gcXVlOgoKSSAtICBvIGNvbnRlw7pkbyBkaXNwb25pYmlsaXphZG8gw6kgZGUgcmVzcG9uc2FiaWxpZGFkZSBkZSBzdWEgYXV0b3JpYTsKCklJIC0gbyBjb250ZcO6ZG8gw6kgb3JpZ2luYWwsIGUgc2UgbyB0cmFiYWxobyBlL291IHBhbGF2cmFzIGRlIG91dHJhcyBwZXNzb2FzIGZvcmFtIHV0aWxpemFkb3MsIGVzdGFzIGZvcmFtIGRldmlkYW1lbnRlIHJlY29uaGVjaWRhczsKCklJSSAtIHF1YW5kbyB0cmF0YXItc2UgZGUgVHJhYmFsaG8gZGUgQ29uY2x1c8OjbyBkZSBDdXJzbywgRGlzc2VydGHDp8OjbyBvdSBUZXNlOiBvIGFycXVpdm8gZGVwb3NpdGFkbyBjb3JyZXNwb25kZSDDoCB2ZXJzw6NvIGZpbmFsIGRvIHRyYWJhbGhvOwoKSVYgLSBxdWFuZG8gdHJhdGFyLXNlIGRlIFRyYWJhbGhvIGRlIENvbmNsdXPDo28gZGUgQ3Vyc28sIERpc3NlcnRhw6fDo28gb3UgVGVzZTogZXN0b3UgY2llbnRlIGRlIHF1ZSBhIGFsdGVyYcOnw6NvIGRhIG1vZGFsaWRhZGUgZGUgYWNlc3NvIGFvIGRvY3VtZW50byBhcMOzcyBvIGRlcMOzc2l0byBlIGFudGVzIGRlIGZpbmRhciBvIHBlcsOtb2RvIGRlIGVtYmFyZ28sIHF1YW5kbyBmb3IgZXNjb2xoaWRvIGFjZXNzbyByZXN0cml0bywgc2Vyw6EgcGVybWl0aWRhIG1lZGlhbnRlIHNvbGljaXRhw6fDo28gZG8gKGEpIGF1dG9yIChhKSBhbyBTaXN0ZW1hIEludGVncmFkbyBkZSBCaWJsaW90ZWNhcyBkYSBVRlBFIChTSUIvVUZQRSkuCgogClBhcmEgdHJhYmFsaG9zIGVtIEFjZXNzbyBBYmVydG86CgpOYSBxdWFsaWRhZGUgZGUgdGl0dWxhciBkb3MgZGlyZWl0b3MgYXV0b3JhaXMgZGUgYXV0b3IgcXVlIHJlY2FlbSBzb2JyZSBlc3RlIGRvY3VtZW50bywgZnVuZGFtZW50YWRvIG5hIExlaSBkZSBEaXJlaXRvIEF1dG9yYWwgbm8gOS42MTAsIGRlIDE5IGRlIGZldmVyZWlybyBkZSAxOTk4LCBhcnQuIDI5LCBpbmNpc28gSUlJLCBhdXRvcml6byBhIFVuaXZlcnNpZGFkZSBGZWRlcmFsIGRlIFBlcm5hbWJ1Y28gYSBkaXNwb25pYmlsaXphciBncmF0dWl0YW1lbnRlLCBzZW0gcmVzc2FyY2ltZW50byBkb3MgZGlyZWl0b3MgYXV0b3JhaXMsIHBhcmEgZmlucyBkZSBsZWl0dXJhLCBpbXByZXNzw6NvIGUvb3UgZG93bmxvYWQgKGFxdWlzacOnw6NvKSBhdHJhdsOpcyBkbyBzaXRlIGRvIFJlcG9zaXTDs3JpbyBEaWdpdGFsIGRhIFVGUEUgbm8gZW5kZXJlw6dvIGh0dHA6Ly93d3cucmVwb3NpdG9yaW8udWZwZS5iciwgYSBwYXJ0aXIgZGEgZGF0YSBkZSBkZXDDs3NpdG8uCgogClBhcmEgdHJhYmFsaG9zIGVtIEFjZXNzbyBSZXN0cml0bzoKCk5hIHF1YWxpZGFkZSBkZSB0aXR1bGFyIGRvcyBkaXJlaXRvcyBhdXRvcmFpcyBkZSBhdXRvciBxdWUgcmVjYWVtIHNvYnJlIGVzdGUgZG9jdW1lbnRvLCBmdW5kYW1lbnRhZG8gbmEgTGVpIGRlIERpcmVpdG8gQXV0b3JhbCBubyA5LjYxMCBkZSAxOSBkZSBmZXZlcmVpcm8gZGUgMTk5OCwgYXJ0LiAyOSwgaW5jaXNvIElJSSwgYXV0b3Jpem8gYSBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBQZXJuYW1idWNvIGEgZGlzcG9uaWJpbGl6YXIgZ3JhdHVpdGFtZW50ZSwgc2VtIHJlc3NhcmNpbWVudG8gZG9zIGRpcmVpdG9zIGF1dG9yYWlzLCBwYXJhIGZpbnMgZGUgbGVpdHVyYSwgaW1wcmVzc8OjbyBlL291IGRvd25sb2FkIChhcXVpc2nDp8OjbykgYXRyYXbDqXMgZG8gc2l0ZSBkbyBSZXBvc2l0w7NyaW8gRGlnaXRhbCBkYSBVRlBFIG5vIGVuZGVyZcOnbyBodHRwOi8vd3d3LnJlcG9zaXRvcmlvLnVmcGUuYnIsIHF1YW5kbyBmaW5kYXIgbyBwZXLDrW9kbyBkZSBlbWJhcmdvIGNvbmRpemVudGUgYW8gdGlwbyBkZSBkb2N1bWVudG8sIGNvbmZvcm1lIGluZGljYWRvIG5vIGNhbXBvIERhdGEgZGUgRW1iYXJnby4KRepositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212022-02-15T05:14:59Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
Quantum neurons with real weights for diabetes prediction |
title |
Quantum neurons with real weights for diabetes prediction |
spellingShingle |
Quantum neurons with real weights for diabetes prediction MONTEIRO, Cláudio Luis Alves Inteligência computacional Aprendizado de máquina |
title_short |
Quantum neurons with real weights for diabetes prediction |
title_full |
Quantum neurons with real weights for diabetes prediction |
title_fullStr |
Quantum neurons with real weights for diabetes prediction |
title_full_unstemmed |
Quantum neurons with real weights for diabetes prediction |
title_sort |
Quantum neurons with real weights for diabetes prediction |
author |
MONTEIRO, Cláudio Luis Alves |
author_facet |
MONTEIRO, Cláudio Luis Alves |
author_role |
author |
dc.contributor.authorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/2883009157618518 |
dc.contributor.advisorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/9643216021359436 |
dc.contributor.author.fl_str_mv |
MONTEIRO, Cláudio Luis Alves |
dc.contributor.advisor1.fl_str_mv |
PAULA NETO, Fernando Maciano de |
contributor_str_mv |
PAULA NETO, Fernando Maciano de |
dc.subject.por.fl_str_mv |
Inteligência computacional Aprendizado de máquina |
topic |
Inteligência computacional Aprendizado de máquina |
description |
Parametric models with real numbers valued parameters have greater performance than its counterparts with binary valued weights, due to the gain in representing informa- tion with real values, and therefore having a larger space for memory association. In this work, is proposed a quantum neuron capable of store real weights and preserve the gain of the superposition property, encoding the information in the probability amplitudes of the quantum system, the Real Weights Quantum Neuron. Its performance is compared with other quantum neurons to analyze the application of the quantum neurons on real-world problems, i.e diabetes classification. The results of the experiments shows that a single quantum neuron is capable of achieving an accuracy rate of 100% in the XOR problem and an accuracy rate of 100% in a non-linear dataset, demonstrating that the quantum neurons with real weights are capable of modeling non-linearly separable problems. In the problem of diagnosing diabetes, quantum neurons achieved an accuracy rate of 76% and AUC-ROC of 88%, while its classic version, the perceptron, reached only 63% accuracy and the artificial neural network reached 80% AUC-ROC. These results indicate that a single quantum neuron performs better than its classical version and even the artificial neural network for AUC-ROC, demonstrating potential for use in healthcare applications in the near future. This work is also a contribution to the field of quantum neural networks, which can be further advanced from the quantum neuron proposed. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021-09-02 |
dc.date.accessioned.fl_str_mv |
2022-02-14T13:31:00Z |
dc.date.available.fl_str_mv |
2022-02-14T13:31:00Z |
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 |
MONTEIRO, Cláudio Luis Alves. Quantum neurons with real weights for diabetes prediction. 2021. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Pernambuco, Recife, 2021. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/42831 |
identifier_str_mv |
MONTEIRO, Cláudio Luis Alves. Quantum neurons with real weights for diabetes prediction. 2021. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Pernambuco, Recife, 2021. |
url |
https://repositorio.ufpe.br/handle/123456789/42831 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pos Graduacao em Ciencia da Computacao |
dc.publisher.initials.fl_str_mv |
UFPE |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFPE instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Repositório Institucional da UFPE |
collection |
Repositório Institucional da UFPE |
bitstream.url.fl_str_mv |
https://repositorio.ufpe.br/bitstream/123456789/42831/1/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdf https://repositorio.ufpe.br/bitstream/123456789/42831/2/license.txt https://repositorio.ufpe.br/bitstream/123456789/42831/3/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdf.txt https://repositorio.ufpe.br/bitstream/123456789/42831/4/DISSERTA%c3%87%c3%83O%20Cl%c3%a1udio%20Luis%20Alves%20Monteiro.pdf.jpg |
bitstream.checksum.fl_str_mv |
abc7f380871baaefd2fcce825f98c0fd 6928b9260b07fb2755249a5ca9903395 e3658ba6ea344804da6fbaa872399e68 6d7d26ef4212c5dd0ae7766dc6396ab9 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
attena@ufpe.br |
_version_ |
1802310852495278080 |