This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces
Feb. 2013 (vol. 35 no. 2)
pp. 286-299
Heung-Il Suk, Dept. of Comput. Sci. & Eng., Korea Univ., Seoul, South Korea
Seong-Whan Lee, Dept. of Brain & Cognitive Eng., Korea Univ., Seoul, South Korea
As there has been a paradigm shift in the learning load from a human subject to a computer, machine learning has been considered as a useful tool for Brain-Computer Interfaces (BCIs). In this paper, we propose a novel Bayesian framework for discriminative feature extraction for motor imagery classification in an EEG-based BCI in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches. In our framework, the problem of simultaneous spatiospectral filter optimization is formulated as the estimation of an unknown posterior probability density function (pdf) that represents the probability that a single-trial EEG of predefined mental tasks can be discriminated in a state. In order to estimate the posterior pdf, we propose a particle-based approximation method by extending a factored-sampling technique with a diffusion process. An information-theoretic observation model is also devised to measure discriminative power of features between classes. From the viewpoint of classifier design, the proposed method naturally allows us to construct a spectrally weighted label decision rule by linearly combining the outputs from multiple classifiers. We demonstrate the feasibility and effectiveness of the proposed method by analyzing the results and its success on three public databases.
Index Terms:
spatial filters,approximation theory,Bayes methods,brain-computer interfaces,electroencephalography,feature extraction,information theory,learning (artificial intelligence),medical signal processing,sampling methods,signal classification,spectrally weighted label decision rule,Bayesian framework,discriminative feature extraction,brain-computer interfaces,machine learning,motor imagery classification,EEG-based BCI,class-discriminative frequency bands,spatial filters,probabilistic approach,information-theoretic approach,spatiospectral filter optimization,posterior probability density function,pdf,mental tasks,particle-based approximation method,factored-sampling technique,diffusion process,information-theoretic observation model,classifier design,Electroencephalography,Optimization,Feature extraction,Machine learning,Estimation,Probability density function,Brain computer interfaces,motor imagery classification,Discriminative feature extraction,spatiospectral filter optimization,Brain-Computer Interface (BCI),ElectroEncephaloGraphy (EEG)
Citation:
Heung-Il Suk, Seong-Whan Lee, "A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 2, pp. 286-299, Feb. 2013, doi:10.1109/TPAMI.2012.69
Usage of this product signifies your acceptance of the Terms of Use.