Suggestion of a hybrid computational model to optimize EEG motor imagery signals classification

Brain-computer interfaces (BCIs) have proven to be innovative and promising technologies for human-machine interaction. However, distinguishing with relative precision between EEG motor signals generated by real or imagined movements of the left and right hands has still been a major challenge. By analyzing brain electrical signals and the processes of reading, processing, and interpreting data, the hybrid model suggested in this dissertation contributed to greater effectiveness of the algorithms, with accuracy above that normally found in most models present in the most recent literature. The experimental and observational research carried out in the creation of the methodology applied in this dissertation ensures the replication of automation methods, techniques, and algorithms, machine learning, and more specifically, in data preparation, feature extraction, signal classification, and obtaining results with greater accuracy for the implementation of brain-computer interfaces, BCIs. This dissertation opens new possibilities for future research and deepening of techniques, tools, and new experiments. With a premise to create personalized BCIs and trained specifically for individual pattern recognition, as they have shown greater potential results. Each human being is unique and has singular characteristics that distinguish them from all other beings.