2025-08-192025-08-192025-08-13AZEVEDO, João Lucas Santos. Análise de classificadores multiclasse aplicados a sinais de EEG baseados em SSVEP. Orientador: Cleison Daniel Silva. 2025. 54 f. Trabalho de Conclusão de Curso (Bacharelado em Engenharia Elétrica) – Faculdade de Engenharia Elétrica, Campus Universitário de Tucuruí, Universidade Federal do Pará, Tucuruí, 2025. Disponível em: https://bdm.ufpa.br/handle/prefix/8491. Acesso em:.https://bdm.ufpa.br/handle/prefix/8491Brain-Computer Interfaces (BCIs) have been gaining increasing prominence in academic research, with their optimization and refinement becoming a major focus in the fields of engineering and neuroscience. This is largely due to their potential to promote autonomy and improve quality of life, especially for individuals with motor impairments. Among the various approaches, BCIs based on Steady-State Visually Evoked Potentials (SSVEPs) stand out for their practicality and simplicity in converting visual stimuli into commands. SSVEP-based BCI systems rely on brain responses to visual stimuli calibrated at specific frequencies, which are interpreted as distinct commands for use in external devices or digital applications. In this context, the present study conducts a comparative analysis of multiclass classifiers applied to EEG signals acquired through the SSVEP paradigm, using public data from RIKEN-LABSP. Various feature extraction and preprocessing strategies were implemented prior to applying the Linear Discriminant Analysis (LDA), K Nearest Kneighbors (KNN) and Random Forest classifiers. The results demonstrate the feasibility of the approach, with maximum accuracies of 100%, 83.33%, and 74.81% for time windows of 2 s, 1 s, and 500 ms, respectively. The LDA classifier achieved the best performance among those evaluated, proving to be the most suitable for the proposed task.Acesso AbertoEletroencefalografiaSSVEPClassificação multiclasseOtimizaçãoAprendizado de máquinaElectroencephalographyMulticlass ClassificationOptimizationMachine LearningCNPQ::ENGENHARIAS::ENGENHARIA BIOMEDICA::BIOENGENHARIA::PROCESSAMENTO DE SINAIS BIOLOGICOSCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAOTrabalho de Curso - Graduação - MonografiaAttribution-NonCommercial-NoDerivs 3.0 Brazil