A Latent Discriminative Model-Based Approach for Classification of Imaginary Motor Tasks from EEG Data
Jaime Fernando Delgado Saa and Müjdat Çetin
Journal of Neural Engineering, 9, 026020, 2012.
Abstract. We consider the problem of classiﬁcation of imaginary motor tasks from electroencephalography (EEG) data for brain-computer interfaces (BCIs) and propose a new approach based on hidden conditional random ﬁelds (HCRFs). HCRFs are discriminative graphical models that are attractive for this problem because they (1) exploit the temporal structure of EEG; (2) include latent variables that can be used to model diﬀerent brain states in the signal; and (3) involve learned statistical models matched to the classiﬁcation task, avoiding some of the limitations of generative models. Our approach involves spatial ﬁltering of the EEG signals and estimation of power spectra based on auto-regressive modeling of temporal segments of the EEG signals. Given this time-frequency representation, we select certain frequency bands that are known to be associated with execution of motor tasks. These selected features constitute the data that are fed to the HCRF, parameters of which are learned from training data. Inference algorithms on the HCRFs are used for classiﬁcation of motor tasks. We experimentally compare this approach to the best performing methods in BCI competition IV as well as a number of more recent methods and observe that our proposed method yields better classiﬁcation accuracy.