Reconhecimento de gestos por sinais eletromiográficos para um jogo voltado à reabilitação de mãos e punho

• Ano de defesa: 2017
• Autor(a) principal: Batista, Thiago Vinícius Vieira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal da Paraíba; Brasil; Ciências Exatas e da Saúde; Programa de Pós-Graduação em Modelos de Decisão e Saúde; UFPB
• Palavras-chave em Português: Interação natural; Serious games; Reabilitação; Eletromiografia; Natural Interaction; Serious Games; Rehabilitation; Electromyography; CIENCIAS DA SAUDE::SAUDE COLETIVA
• Link de acesso: https://repositorio.ufpb.br/jspui/handle/tede/9071

One of the strategies being used in recent years to increase the commitment and motivation of patients undergoing rehabilitation is the use of computer systems, such as virtual environments and serious games. In addition to contributing to the motivation, these systems can simulate real life activities and provide means to measure and assess user performance. The use of natural interaction devices originally conceived for the game market has allowed the development of low cost and minimally invasive rehabilitation systems. With the advent of natural interaction devices based on electromyography, the user's eletromyographic data could also be used to build these systems. Therefore, the goal of this work is to build a low-cost serious game to aid in the rehabilitation process of patients with hand motor problems, allowing that the system contribute to patient motivation during the treatment. The systems uses an electromyography device to recognize the gestures being performed by the user through the incorporation of an decision model based on neural networks, which is responsible for interpreting the signals.