A latent discriminative model-based approach for classification of imaginary motor tasks from EEG data

Warning The system is temporarily closed to updates for reporting purpose.

Delgado Saa, Jaime Fernando and Çetin, Müjdat (2012) A latent discriminative model-based approach for classification of imaginary motor tasks from EEG data. Journal of Neural Engineering, 9 (2). ISSN 1741-2560

This is the latest version of this item.

PDF (This is a RoMEO green journal -- author can archive post-print (ie final draft post-refereeing)) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1088/1741-2560/9/2/026020


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.

Item Type:Article
Additional Information:Article Number: 026020
Uncontrolled Keywords:brain-computer interfaces, motor imagery, electroencephalography, time series analysis, conditional random fields, discriminative models
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:19007
Deposited By:Müjdat Çetin
Deposited On:02 May 2012 15:31
Last Modified:31 Jul 2019 10:52

Available Versions of this Item

Repository Staff Only: item control page