A Minimax Mutual Information Scheme for Supervised Feature Extraction and Its Application to EEG-Based Brain-Computer Interfacing

Oveisi, Farid; Erfanian, Abbas

doi:10.1155/2008/673040

Cited by 18 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to meet this challenge, this paper introduces mutual information, which measures the mutual dependence of two random variables or reduction in uncertainty of random variables. The information-theoretic approach has recently received considerable attention in both the BCI [25], [31], [32] and the machine learning communities [33], [34], [35] for the selection of an informative subset from original features. Unlike that use of mutual information, in this paper, we consider it for the likelihood computation in the proposed Bayesian framework.…”

Section: Likelihood Estimation With Mutual Informationmentioning

confidence: 99%

A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces

Suk

Lee

2013

IEEE Trans. Pattern Anal. Mach. Intell.

223

135

View full text Add to dashboard Cite

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.

show abstract

Section: Likelihood Estimation With Mutual Informationmentioning

confidence: 99%

A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces

Suk

Lee

2013

IEEE Trans. Pattern Anal. Mach. Intell.

223

135

View full text Add to dashboard Cite

show abstract

“…Let S ( t ) and D ( t ) , respectively, be a set of the candidate SFVPs and a current optimal spatial filter composed of the class‐discriminative SFVPs, which we call “Discriminative Spatial Filter Vector Pairs” (DSFVPs), at the t th iteration. The class‐discriminative power of DSFVPs is evaluated by means of mutual information between feature vectors and class labels that has been widely used in both the BCI (Zhang et al, ; Lan et al, ; Oveisi and Erfanian, ; Suk and Lee, ) and the machine learning communities (Kwak and Choi, ; Peng et al, ; Leiva‐Murillo and Artés‐Rodríguez, ) for feature selection. The computational issue for mutual information is covered in the next subsection.…”

Section: Class‐discriminative Spatial Filter Selectionmentioning

confidence: 99%

Designing discriminative spatial filter vectors in motor imagery brain–computer interface

Lee

Kim

2013

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The problem of a volume conduction effect in electroencephalography is considered one of the challenging issues in brain-computer interface (BCI) community. In this article, we propose a novel method of designing a class-discriminative spatial filter assuming that a combination of spatial pattern vectors, irrespective of the eigenvalues of the common spatial pattern (CSP), can produce better performance in terms of classification accuracy. We select discriminative spatial filter vectors that determine features in a pairwise manner, that is, eigenvectors of the K largest eigenvalue and the K smallest eigenvalue. Although the pair of the eigenvectors of the K largest and the K smallest eigenvalues helps extract discriminative features, we believe that a different set of eigenvector pairs is more appropriate to extract class-discriminative features. In our experimental results using the publicly available dataset of BCI Competition IV, we show that the proposed method outperformed the conventional CSP methods and a filter-bank CSP.

show abstract

“…It is also assumed that both the mixture variables and the independent components have zero mean (Oveisi et al, 2008).…”

Section: Genetic Algorithmmentioning

confidence: 99%

Nonlinear Independent Component Analysis for EEG-Based Brain-Computer Interface Systems

Oveisi¹,

Oveisi²,

Efranian³

et al. 2012

Independent Component Analysis for Audio and Biosignal Applications

Self Cite

View full text Add to dashboard Cite

A Minimax Mutual Information Scheme for Supervised Feature Extraction and Its Application to EEG-Based Brain-Computer Interfacing

Cited by 18 publications

References 16 publications

A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces

A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces

Designing discriminative spatial filter vectors in motor imagery brain–computer interface

Nonlinear Independent Component Analysis for EEG-Based Brain-Computer Interface Systems

Contact Info

Product

Resources

About