Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012 Mar 29:6:39.
doi: 10.3389/fnins.2012.00039. eCollection 2012.

Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b

Kai Keng Ang  1 , Zheng Yang Chin, Chuanchu Wang, Cuntai Guan, Haihong Zhang
Affiliations

Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b

Kai Keng Ang et al. Front Neurosci. .

Abstract

The Common Spatial Pattern (CSP) algorithm is an effective and popular method for classifying 2-class motor imagery electroencephalogram (EEG) data, but its effectiveness depends on the subject-specific frequency band. This paper presents the Filter Bank Common Spatial Pattern (FBCSP) algorithm to optimize the subject-specific frequency band for CSP on Datasets 2a and 2b of the Brain-Computer Interface (BCI) Competition IV. Dataset 2a comprised 4 classes of 22 channels EEG data from 9 subjects, and Dataset 2b comprised 2 classes of 3 bipolar channels EEG data from 9 subjects. Multi-class extensions to FBCSP are also presented to handle the 4-class EEG data in Dataset 2a, namely, Divide-and-Conquer (DC), Pair-Wise (PW), and One-Versus-Rest (OVR) approaches. Two feature selection algorithms are also presented to select discriminative CSP features on Dataset 2b, namely, the Mutual Information-based Best Individual Feature (MIBIF) algorithm, and the Mutual Information-based Rough Set Reduction (MIRSR) algorithm. The single-trial classification accuracies were presented using 10 × 10-fold cross-validations on the training data and session-to-session transfer on the evaluation data from both datasets. Disclosure of the test data labels after the BCI Competition IV showed that the FBCSP algorithm performed relatively the best among the other submitted algorithms and yielded a mean kappa value of 0.569 and 0.600 across all subjects in Datasets 2a and 2b respectively.

Keywords: Bayesian classification; brain-computer interface; electroencephalogram; feature selection; mutual information.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Architecture of the filter bank common spatial pattern (FBCSP) algorithm for the training and evaluation phases.
Figure 2
Figure 2
The illustration on the extraction of a single-trial EEG segment from the training data for the multi-class FBCSP training phase in Dataset 2a, and the generation of the classification outputs using the multi-class extension to FBCSP on the entire time segment of a single-trial for the evaluation phase.
Figure 3
Figure 3
The illustration on the extraction of a single-trial EEG segment from the training data for the FBCSP training phase in Dataset 2b, and the generation of the classification outputs using FBCSP on the entire time segment of a single-trial for the evaluation phase.
See this image and copyright information in PMC

References

    1. Ang K. K., Chin Z. Y., Zhang H., Guan C. (2008). “Filter bank common spatial pattern (FBCSP) in brain-computer interface,” in Proceedings of the IEEE International Joint Conference on Neural Networks, Hong Kong, 2391–2398
    1. Ang K. K., Quek C. (2005). RSPOP: rough set-based pseudo outer-product fuzzy rule identification algorithm. Neural Comput. 17, 205–24310.1162/0899766052530857 - DOI - PubMed
    1. Ang K. K., Quek C. (2006). “Rough set-based neuro-fuzzy system,” in Proceedings of the IEEE International Joint Conference on Neural Networks, Vancouver, BC, 742–749
    1. Ang K. K., Quek C. (2012). Supervised pseudo self-evolving cerebellar algorithm for generating fuzzy membership functions. Expert Syst. Appl. 39, 2279–228710.1016/j.eswa.2011.08.001 - DOI
    1. Blankertz B., Dornhege G., Krauledat M., Müller K.-R., Curio G. (2007). The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects. Neuroimage 37, 539–55010.1016/j.neuroimage.2007.01.051 - DOI - PubMed