The non-stationary nature of electroencephalogram (EEG) is a major issue to robust operation of brain-computer interfaces (BCIs). The objective of this paper is to propose an adaptive classification framework whereby a processing stage is introduced before classification to address non-stationarity in EEG classification. Features extracted from EEG signals are adaptively processed before classification to reduce the small fluctuations between calibration and evaluation data. In this way, static classifiers can be employed in non-stationary environments without additional changes. The session-to-session performance of the proposed adaptive approach is evaluated on a multiclass problem posed in the BCI Competition IV dataset 2a. A probabilistic generative model was used as a classification algorithm. The results yields a significantly higher mean kappa of 0.62 compared to 0.58 from the baseline probabilistic generative model without adaptive processing. Also, the proposed approach outperforms the winner of the BCI Competition IV dataset 2a. These results suggest a promising approach separating adaptation-related tasks and classification. © Springer International Publishing Switzerland 2014.
CITATION STYLE
Nicolas-Alonso, L. F., Corralejo, R., Álvarez, D., & Hornero, R. (2014). Adaptive Classification Framework for Multiclass Motor Imagery-Based BCI. In IFMBE Proceedings (Vol. 41, pp. 762–765). Springer Verlag. https://doi.org/10.1007/978-3-319-00846-2_189
Mendeley helps you to discover research relevant for your work.