Brain-Computer Interface (BCI) is a rapidly developing technology that aims to support individuals suffering from various\ndisabilities and, ultimately, improve everyday quality of life. Sensorimotor rhythm-based BCIs have demonstrated remarkable\nresults in controlling virtual or physical external devices but they still face a number of challenges and limitations. Main challenges\ninclude multiple degrees-of-freedom control, accuracy, and robustness. In this work, we develop a multiclass BCI decoding\nalgorithm that uses electroencephalography (EEG) source imaging, a technique that maps scalp potentials to cortical activations,\nto compensate for low spatial resolution of EEG. Spatial features were extracted using Common Spatial Pattern (CSP) filters in the\ncortical source space from a number of selected Regions of Interest (ROIs). Classification was performed through an ensemble\nmodel, based on individual ROI classification models. The evaluation was performed on the BCI Competition IV dataset 2a, which\nfeatures 4 motor imagery classes from 9 participants. Our results revealed a mean accuracy increase of 5.6% with respect to the\nconventional application method of CSP on sensors. Neuroanatomical constraints and prior neurophysiological knowledge play\nan important role in developing source space-based BCI algorithms. Feature selection and classifier characteristics of our\nimplementation will be explored to raise performance to current state-of-the-art.
Loading....