Classification of EEG Multiple Imagination Tasks Based on Independent Component Analysis and Relevant Vector Machines

To solve the problem of feature extraction in braincomputer interface (BCI), the position, size and direction of dipole are located by using dipole localization method, so as to locate the active part of advanced nerve activity and remove a series of physiological and electrical artifacts such as electro-ophthalmogram. The common space pattern and correlation vector machine are used to extract the effective components of EEG signals and classify multiple motor imagery tasks. The results show that the combination of EEG dipole localization and common spatial pattern can effectively improve the signal-to-noise ratio of EEG signals and extract more obvious features. The correlation vector machine provides better classification results and is an effective method to complete the classification and recognition of motor imagery signals.

[1]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[2]  Cuntai Guan,et al.  Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms , 2011, IEEE Transactions on Biomedical Engineering.

[3]  Wolfgang Rosenstiel,et al.  An MEG-based brain–computer interface (BCI) , 2007, NeuroImage.

[4]  G. Schalk,et al.  Brain-Computer Interfaces Using Electrocorticographic Signals , 2011, IEEE Reviews in Biomedical Engineering.

[5]  Wolfgang Grodd,et al.  Principles of a brain-computer interface (BCI) based on real-time functional magnetic resonance imaging (fMRI) , 2004, IEEE Transactions on Biomedical Engineering.

[6]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[7]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[8]  N. Birbaumer.  Breaking the silence: brain-computer interfaces (BCI) for communication and motor control. , 2006, Psychophysiology.

[9]  M. Scheutz,et al.  Limitations of NIRS-Based BCI for Realistic Applications in Human-Computer Interaction , 2013 .

[10]  L. Zhukov,et al.  Independent component analysis for EEG source localization , 2000, IEEE Engineering in Medicine and Biology Magazine.

[11]  Gert Pfurtscheller,et al.  Motor imagery and direct brain-computer communication , 2001, Proc. IEEE.

[12]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[13]  J. Gotman,et al.  Systematic source estimation of spikes by a combination of independent component analysis and RAP-MUSIC I: Principles and simulation study , 2002, Clinical Neurophysiology.

[14]  Enzeng Dong,et al.  Classification of four categories of EEG signals based on relevance vector machine , 2017, 2017 IEEE International Conference on Mechatronics and Automation (ICMA).

[15]  Chao Chen,et al.  Improved common spatial pattern for brain-computer interfacing , 2015, 2015 IEEE International Conference on Mechatronics and Automation (ICMA).

[16]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.