Publicação

Device control system based on classified EMG signals: a machine learning approach

Ver documento

Detalhes bibliográficos
Resumo:In contemporary society, certain physical attributes are celebrated, while others are stigmatized, leading to barriers in the social inclusion of individuals who do not conform to these idealized standards. People with disabilities (PwD) often face societal prejudices, further exacerbated by the absence of adaptive tools, pushing them away from a conventional life. Approximately 15% of the global population has some form of disability, with a significant portion experiencing physical disabilities related to upper limbs. Among these, many undergo amputation, a transformative process that affects both their physical and psychological well-being. Prostheses, while beneficial, have limitations in replicating the full range of limb movements and are often financially inaccessible to many. This research proposes an innovative system that leverages the retained ability of amputees to generate electromyographic (EMG) signals post-amputation. The system aims to control electronic devices directly through these signals, bypassing the need for prosthetics. Potential applications include replacing traditional computer mice and controlling gaming platforms. The core design is a compact bracelet equipped with non-invasive EMG sensors, an accelerometer, and a gyroscope. Data from these sensors are processed using artificial intelligence techniques to generate device-specific commands. The overarching goal is to enhance the autonomy and social integration of amputees, while also contributing to technological advancements in the field.
Autores principais:Barbosa, Ana Carolina
Assunto:Electromyographic (EMG) signals Artificial intelligence People with disabilities (PwD)
Ano:2024
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
Descrição
Resumo:In contemporary society, certain physical attributes are celebrated, while others are stigmatized, leading to barriers in the social inclusion of individuals who do not conform to these idealized standards. People with disabilities (PwD) often face societal prejudices, further exacerbated by the absence of adaptive tools, pushing them away from a conventional life. Approximately 15% of the global population has some form of disability, with a significant portion experiencing physical disabilities related to upper limbs. Among these, many undergo amputation, a transformative process that affects both their physical and psychological well-being. Prostheses, while beneficial, have limitations in replicating the full range of limb movements and are often financially inaccessible to many. This research proposes an innovative system that leverages the retained ability of amputees to generate electromyographic (EMG) signals post-amputation. The system aims to control electronic devices directly through these signals, bypassing the need for prosthetics. Potential applications include replacing traditional computer mice and controlling gaming platforms. The core design is a compact bracelet equipped with non-invasive EMG sensors, an accelerometer, and a gyroscope. Data from these sensors are processed using artificial intelligence techniques to generate device-specific commands. The overarching goal is to enhance the autonomy and social integration of amputees, while also contributing to technological advancements in the field.