Motor imagery classification in brain-machine interface with machine learning algorithms: Classical approach to multi-layer perceptron model

Abstract

Motor Imagery classification is a major topic in Brain-Computer Interface (BCI) because of its value for clinical restoration of impaired motor ability. Compared to the classical approaches combined with Machine Learning (ML) algorithms are primarily investigated during the past decade, the number of studies that employ Deep Learning methods on BCI applications is relatively limited. In this study, we aim to provide a comprehensive comparison between traditional classification methods and suggests the significance of Deep Learning-based BCI techniques, especially Multi-Layered Perceptron. In summary, with Electroencephalography (EEG) signals during motor imagery tasks, Support Vector Machine (SVM) showed the shortest training time and prediction speed with comparable accuracy among traditional ML-based algorithms. Notably, our subject-independent generalized MLP model succsfully classified the signals with ≈90% accuracy and half the classification time compared to traditional ML-based models. (1) This result suggests that this standard MLP model can become a bridging wireframe for further advanced subject-independent BCI with sophisticated optimization. (2) This result suggests the possibility of a much accurate and robust generalized BCI (subject independent) if this model integrates sophisticated optimization.