SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications

Detalhes bibliográficos
Autor(a) principal: Giovanini, Renato de Macedo [UNESP]
Data de Publicação: 2017
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://hdl.handle.net/11449/151710
Resumo: There are, nowadays, about 110 million people in the world who live with some type of severe motor disability. Specifically in Brazil, about 2.2% of the population are estimated to live with a condition of difficult locomotion. Aiming to help these people, a vast variety of devices, techniques and services are currently being developed. Among those, one of the most complex and challenging techniques is the study and development of Brain-Computer Interfaces (BCIs). BCIs are systems that allow the user to communicate with the external world controlling devices without the use of muscles or peripheral nerves, using only his decoded brain activity. To achieve this, there is a need to develop robust pattern recognition systems, that must be able to detect the user’s intention through electroencephalography (EEG) signals and activate the corresponding output with reliable accuracy and within the shortest possible processing time. In this work, different EEG signal processing techniques were studied, and it is presented the development of a EEG under visual stimulation (Steady-State Visual Evoked Potentials - SSVEP) pattern recognition system. Using only Open Source tools and Python programming language, modules to manage datasets, reduce noise, extract features and perform classification of EEG signals were developed, and a comparative study of different techniques was performed, using filter banks and Discrete Wavelet Transforms (DWT) as feature extraction approaches, and the classifiers K-Nearest Neighbors, Multilayer Perceptron and Random Forests. Using DWT approach with Random Forest and Multilayer Perceptron classifiers, high accuracy rates up to 92 % were achieved in deeper decomposition levels. Then, the small-size microcomputer Raspberry Pi was used to perform time processing evaluation, obtaining short processing times for every classifiers. This work is a preliminary study of BCIs at the Laboratório de Instrumentação e Engenharia Biomédica, and, in the future, the system here presented may be part of a complete SSVEP-BCI system.
id UNSP_0e50fb944f1eabdcc89a3bf204a513bb
oai_identifier_str oai:repositorio.unesp.br:11449/151710
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applicationsSistema de reconhecimento de padrões de sinais SSVEP-EEG para aplicações em interfaces cérebro-computadorPattern recognitionMachine learningBrain-machine interfaceBrain-computer interfacePythonRaspberry PiOpen-sourceReconhecimento de padrõesAprendizado de máquinaInterface cérebro-máquinaInterface cérebro-computadorThere are, nowadays, about 110 million people in the world who live with some type of severe motor disability. Specifically in Brazil, about 2.2% of the population are estimated to live with a condition of difficult locomotion. Aiming to help these people, a vast variety of devices, techniques and services are currently being developed. Among those, one of the most complex and challenging techniques is the study and development of Brain-Computer Interfaces (BCIs). BCIs are systems that allow the user to communicate with the external world controlling devices without the use of muscles or peripheral nerves, using only his decoded brain activity. To achieve this, there is a need to develop robust pattern recognition systems, that must be able to detect the user’s intention through electroencephalography (EEG) signals and activate the corresponding output with reliable accuracy and within the shortest possible processing time. In this work, different EEG signal processing techniques were studied, and it is presented the development of a EEG under visual stimulation (Steady-State Visual Evoked Potentials - SSVEP) pattern recognition system. Using only Open Source tools and Python programming language, modules to manage datasets, reduce noise, extract features and perform classification of EEG signals were developed, and a comparative study of different techniques was performed, using filter banks and Discrete Wavelet Transforms (DWT) as feature extraction approaches, and the classifiers K-Nearest Neighbors, Multilayer Perceptron and Random Forests. Using DWT approach with Random Forest and Multilayer Perceptron classifiers, high accuracy rates up to 92 % were achieved in deeper decomposition levels. Then, the small-size microcomputer Raspberry Pi was used to perform time processing evaluation, obtaining short processing times for every classifiers. This work is a preliminary study of BCIs at the Laboratório de Instrumentação e Engenharia Biomédica, and, in the future, the system here presented may be part of a complete SSVEP-BCI system.Existem, atualmente, cerca de 110 milhões de pessoas no mundo que vivem com algum tipo de deficiência motora severa. Especificamente no Brasil, é estimado que cerca de 2.2% da população conviva com alguma condição que dificulte a locomoção. Com o intuito de auxiliar tais pessoas, uma grande variedade de dispositivos, técnicas e serviços são atualmente desenvolvidos. Dentre elas, uma das técnicas mais complexas e desafiadoras é o estudo e o desenvolvimento de Interfaces Cérebro-Computador (ICMs). As ICMs são sistemas que permitem ao usuário comunicar-se com o mundo externo, controlando dispositivos sem o uso de músculos ou nervos periféricos, utilizando apenas sua atividade cerebral decodificada. Para alcançar isso, existe a necessidade de desenvolvimento de sistemas robustos de reconhecimento de padrões, que devem ser capazes de detectar as intenções do usuáro através dos sinais de eletroencefalografia (EEG) e ativar a saída correspondente com acurácia confiável e o menor tempo de processamento possível. Nesse trabalho foi realizado um estudo de diferentes técnicas de processamento de sinais de EEG, e o desenvolvimento de um sistema de reconhecimento de padrões de sinais de EEG sob estimulação visual (Potenciais Evocados Visuais de Regime Permanente - PEVRP). Utilizando apenas técnicas de código aberto e a linguagem Python de programação, foram desenvolvidos módulos para realizar o gerenciamento de datasets, redução de ruído, extração de características e classificação de sinais de EEG, e um estudo comparativo de diferentes técnicas foi realizado, utilizando-se bancos de filtros e a Transformada Wavelet Discreta (DWT) como abordagens de extração de características, e os classificadores K-Nearest Neighbors, Perceptron Multicamadas e Random Forests. Utilizando-se a DWT juntamente com Random Forests e Perceptron Multicamadas, altas taxas de acurácia de até 92 % foram obtidas nos níveis mais profundos de decomposição. Então, o computador Raspberry Pi, de pequenas dimensões, foi utilizado para realizar a avaliação do tempo de processamento, obtendo um baixo tempo de processamento para todos os classificadores. Este trabalho é um estudo preliminar em ICMs no Laboratório de Instrumentação e Engenharia Biomédica e, no futuro, pode ser parte de um sistema ICM completo.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Universidade Estadual Paulista (Unesp)Carvalho, Aparecido Augusto de [UNESP]Universidade Estadual Paulista (Unesp)Giovanini, Renato de Macedo [UNESP]2017-09-27T20:24:55Z2017-09-27T20:24:55Z2017-08-18info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/11449/15171000089240433004099080P0enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESP2024-08-05T17:40:38Zoai:repositorio.unesp.br:11449/151710Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:40:38Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
Sistema de reconhecimento de padrões de sinais SSVEP-EEG para aplicações em interfaces cérebro-computador
title SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
spellingShingle SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
Giovanini, Renato de Macedo [UNESP]
Pattern recognition
Machine learning
Brain-machine interface
Brain-computer interface
Python
Raspberry Pi
Open-source
Reconhecimento de padrões
Aprendizado de máquina
Interface cérebro-máquina
Interface cérebro-computador
title_short SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
title_full SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
title_fullStr SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
title_full_unstemmed SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
title_sort SSVEP-EEG signal pattern recognition system for real-time brain-computer interfaces applications
author Giovanini, Renato de Macedo [UNESP]
author_facet Giovanini, Renato de Macedo [UNESP]
author_role author
dc.contributor.none.fl_str_mv Carvalho, Aparecido Augusto de [UNESP]
Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Giovanini, Renato de Macedo [UNESP]
dc.subject.por.fl_str_mv Pattern recognition
Machine learning
Brain-machine interface
Brain-computer interface
Python
Raspberry Pi
Open-source
Reconhecimento de padrões
Aprendizado de máquina
Interface cérebro-máquina
Interface cérebro-computador
topic Pattern recognition
Machine learning
Brain-machine interface
Brain-computer interface
Python
Raspberry Pi
Open-source
Reconhecimento de padrões
Aprendizado de máquina
Interface cérebro-máquina
Interface cérebro-computador
description There are, nowadays, about 110 million people in the world who live with some type of severe motor disability. Specifically in Brazil, about 2.2% of the population are estimated to live with a condition of difficult locomotion. Aiming to help these people, a vast variety of devices, techniques and services are currently being developed. Among those, one of the most complex and challenging techniques is the study and development of Brain-Computer Interfaces (BCIs). BCIs are systems that allow the user to communicate with the external world controlling devices without the use of muscles or peripheral nerves, using only his decoded brain activity. To achieve this, there is a need to develop robust pattern recognition systems, that must be able to detect the user’s intention through electroencephalography (EEG) signals and activate the corresponding output with reliable accuracy and within the shortest possible processing time. In this work, different EEG signal processing techniques were studied, and it is presented the development of a EEG under visual stimulation (Steady-State Visual Evoked Potentials - SSVEP) pattern recognition system. Using only Open Source tools and Python programming language, modules to manage datasets, reduce noise, extract features and perform classification of EEG signals were developed, and a comparative study of different techniques was performed, using filter banks and Discrete Wavelet Transforms (DWT) as feature extraction approaches, and the classifiers K-Nearest Neighbors, Multilayer Perceptron and Random Forests. Using DWT approach with Random Forest and Multilayer Perceptron classifiers, high accuracy rates up to 92 % were achieved in deeper decomposition levels. Then, the small-size microcomputer Raspberry Pi was used to perform time processing evaluation, obtaining short processing times for every classifiers. This work is a preliminary study of BCIs at the Laboratório de Instrumentação e Engenharia Biomédica, and, in the future, the system here presented may be part of a complete SSVEP-BCI system.
publishDate 2017
dc.date.none.fl_str_mv 2017-09-27T20:24:55Z
2017-09-27T20:24:55Z
2017-08-18
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.uri.fl_str_mv http://hdl.handle.net/11449/151710
000892404
33004099080P0
url http://hdl.handle.net/11449/151710
identifier_str_mv 000892404
33004099080P0
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.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Estadual Paulista (Unesp)
publisher.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.source.none.fl_str_mv reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808128105611526144