Título:	Neuroprostheses control interfaces based on body motion in persons with spinal cord injury
Autor(es):	Fonseca, Lucas Oliveira da
Orientador(es):	Bó, Antônio Padilha Lanari
Assunto:	Lesão medular Estimulação elétrica Aprendizagem de máquina Movimento - análise Interface de usuários
Data de publicação:	18-Jan-2021
Data de defesa:	12-Jul-2019
Referência:	FONSECA, Lucas Oliveira da. Neuroprostheses control interfaces based on body motion in persons with spinal cord injury. 2019. xvi, 133 f., il. Tese (Doutorado em Engenharia Elétrica)—Universidade de Brasília, Brasília, 2019.
Abstract:	Spinal cord injury (SCI) is a serious medical condition that often leads to severe motor disabilities. Persons with SCI may have paraplegia or tetraplegia, greatly decreasing their ability to perform basic tasks such as locomotion, feeding and hygiene. It affects hundreds of thousands of people in Brazil alone and very few people totally recover from it. Traditional recovery treatments such as physiotherapy typically have limited results. A person with SCI may not be able to control their upper or lower limbs, but often the local structures, such as muscles and motoneurons, are preserved. Therefore functional electrical stimulation (FES) can be used to induce contraction on these muscles and generate movement in paralyzed limbs. However, due to their own motor disabilities, patients usually find it hard in their daily lives to operate FES assistive devices. This limits their performance and usability. In this work, I developed a framework of techniques for user interfaces that explore residual motor capabilities that users with SCI may still possess to control neuroprostheses. In order to acquire movement information I use inertial measurement units (IMUs). I developed and evaluated algorithms for detection and classification of movements by users with paraplegia and tetraplegia. They use their own residual movements, depending on their injury levels, to activate different commands in assistive devices. I applied the developed techniques in three application scenarios with persons with SCI. First I performed an experiment in which three users with paraplegia activated an FES device to aid in sitting pivot transfers (SPT). I analyzed their trunk kinematics to investigate the feasibility of using that information to activate the FES on their lower limbs during the SPT. Then I developed an interface with which nine users with tetraplegia used shoulder movements to control a robotic hand, which simulated an upper limb grasping assisted device. In this case, I used accelerometer and gyroscope data along a threshold technique to detect movements, and a principal component analysis (PCA) to classify them. I then mapped these movements into different commands on the robotic hand. Next I developed an interface that uses upper limb kinematics to properly activate an FES neuroprosthesis on lower limbs of persons with paraplegia during FES-rowing. I used a finite state machine and linear discriminant analysis (LDA) to constantly classify every upper limbs movement from the user into three different rowing phases commands. I evaluated it with one participant and an adapted rowing machine for rowers with SCI. On the transfer experiment, each participant moved their trunk in a similar way across trials, with angles standard deviations less than 5°, which means I can use it to automate the FES activation. Using the upper limb grasping simulation interface, participants were able to successfully control the robotic hand, correctly performing 91% of the robotic hand commands I instructed them to. Finally, the rowing protocol participant was capable of rowing with the developed interface with only their upper limbs movements. The system activated his lower limbs neuroprosthesis in sync with the upper limbs rowing motion. Also, he could start and control the FES by stopping or moving his arms. These results show that persons with SCI are successful in using residual motor capabilities to control assistive devices under the observed conditions.
Unidade Acadêmica:	Faculdade de Tecnologia (FT) Departamento de Engenharia Elétrica (FT ENE)
Informações adicionais:	Tese (doutorado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Elétrica, 2019.
Programa de pós-graduação:	Programa de Pós-Graduação em Engenharia Elétrica
Licença:	A concessão da licença deste item refere-se ao termo de autorização impresso assinado pelo autor com as seguintes condições: Na qualidade de titular dos direitos de autor da publicação, autorizo a Universidade de Brasília e o IBICT a disponibilizar por meio dos sites www.bce.unb.br, www.ibict.br, http://hercules.vtls.com/cgi-bin/ndltd/chameleon?lng=pt&skin=ndltd sem ressarcimento dos direitos autorais, de acordo com a Lei nº 9610/98, o texto integral da obra disponibilizada, conforme permissões assinaladas, para fins de leitura, impressão e/ou download, a título de divulgação da produção científica brasileira, a partir desta data.
Agência financiadora:	Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES); Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); Fundação de Apoio à Pesquisa do Distrito Federal (FAP/DF) e Instituto de Engenheiros Eletricistas e Eletrônicos (IEEE).
Aparece nas coleções:	Teses, dissertações e produtos pós-doutorado

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.