Practicing Motor Imagery (MI) with a Brain-Computer Interface (BCI) has shown promise in promoting motor recovery in stroke patients. A BCI records a person’s brain activity and provides feedback to the person in real time, which allows the person to practice his or her brain activity. By imagining a movement (performing MI) such as gripping with their hand, cortical areas in the brain are activated that largely overlaps with those activated during the actual hand movement. A BCI can provide positive feedback when the hand-related cortical areas are activated during MI, which helps a person to learn how to perform MI. Despite evidence that stroke patients may recover some motor function from practicing MI with BCI feedback thanks to the feedback provided from a BCI, the effectiveness and reliability of BCI-based rehabilitation are still poor.  A BCI can detect MI by analyzing patterns of features from the brain activity. The most common features are extracted from the oscillatory activity in the brain.  In BCI research, MI is often treated as a static pattern of features, which is detected by using machine learning algorithms to assign activity into a binary state. However, this model of MI may be inaccurate. Analyzing brain activity as dynamically varying over time and with a continuous measure of strength could better represent the cortical activity related to MI.  In this Licentiate thesis, I explore a method for analyzing the temporal dynamic of MI-activity with a continuous measure of strength. Brain activity was recorded with electroencephalography (EEG) and subject-specific feature patterns were extracted from a group of healthy subjects while they performed MI of two opposing hand movements: opening and closing the hand. Although MI of the two same-hand movements could not be discriminated, the continuous output from a machine learning algorithm was shown to correlate well with MI-related feature patterns. The temporal analysis also revealed that MI is dynamically encoded early, but later stabilizes into a more static pattern of brain activity. Last, to accommodate for higher temporal resolution of MI, I designed and evaluated a BCI framework by its feedback delay and uncertainty as a function of the stress on the system and found a non-linear correlation. These results could be essential for developing a BCI with time-critical feedback. To summarize, in this Licentiate thesis I propose a promising method for analyzing and extracting a temporal representation of MI, enabling relevant and continuous neurofeedback which may contribute to clinical advances in BCI-based stroke rehabilitation.

Orientador: Douglas Domingues Bueno / Resumo: A busca por uma melhor compreensão das regiões do cérebro e suas funções nas ações humanas tem sido uma tarefa árdua, porém muito útil, principalmente para aplicações da engenharia de interface cérebro-máquina (ICM), bem como para o auxílio a diagnósticos médicos a partir de sinais obtidos dos pacientes em avaliação. No contexto do presente trabalho, destacam-se os trabalhos de interface cérebro-máquina (ICM) pela abrangência no envolvimento de técnicas, métodos e ferramentas comumente estudadas nos cursos de engenharia. Em particular, análises envolvendo técnicas de processamento de sinais de eletroencefalograma (EEG) têm se mostrado de significativa importância para o desenvolvimento dessa área. Uma abordagem amplamente utilizada nesse contexto é a ICM usando Potenciais Visuais Evocados de Estados Estacionários (SSVEP, do inglês Steady-State Visual Evoked Potentials), que, de forma geral, são sinais caracterizados pela resposta evocada do cérebro a estímulos visuais modulados em uma frequência específica. Assim, este trabalho tem o objetivo de propor uma generalização do coeficiente de correlação, conceito-base da análise de correlação canônica (CCA), técnica que tem se mostrado robusta e eficiente no reconhecimento de padrões, especialmente no caso dos SSVEP, e detalhar seu comportamento em função dos parâmetros relevantes para se estabelecer melhores práticas de uso em aplicações de ICM, incluindo fatores fisiológicos, técnicos e operacionais. / Abstract: The search for a better understanding of the brain's anatomy and its functions on human actions has been a harsh yet very useful task, especially for brain-computer interface engineering applications, as well as for medical diagnosis using signals from patients. In the context of this work, brain-computer interface (BCI) applications are highlighted due to their compreehensiveness related to techniques, methods and tools commonly studied in engineering. In particular, analyses involving eletroencephalogram (EEG) signals processing have proven to be of great significance for developing this field of study. A widely used approach is Steady State Visual Evoked Potentials (SSVEP) based BCI, which, in general, are signals characterized by the brain’s evoked response to visual stimuli modulated at a certain frequency. This work aims thus to propose a generalization of the correlation coefficient, which entails Canonical Correlation Analysis (CCA), a technique that has presented robustness and efficiency for pattern recognition, especially in SSVEP-based BCIs, and describe its behavior under relevant varying parameters to stablish better use practices in BCI applications, comprising physiological, technical and operational factors. / Mestre