Cultural-Based Multi-Objective Particle Swarm Optimization for EEG Channel Reduction in Multi-Class Brain-Computer Interfaces

Applying many electrodes is undesirable for real-life brain-computer interface (BCI) application since the recording preparation can be troublesome and time-consuming. Multi-objective particle swarm optimization (MOPSO) has been widely utilized to solve multi-objective optimization problems and thus can be employed for channel selection. This paper presented a novel method named cultural-based MOPSO (CMOPSO) for channel selection in motor imagery based BCI. The CMOPSO method introduces a cultural framework to adapt the personalized flight parameters of the mutated particles. A comparison between the proposed algorithm and typical L1-norm algorithm was conducted, and the results showed that the proposed approach is more effective in selecting a smaller subset of channels while maintaining the classification accuracy unreduced.

[1]  Yuhui Ma,et al.  An Unweighted Exhaustive Diagonalization Based Multi-Class Common Spatial Pattern Algorithm in Brain-Computer Interfaces , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[2]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[3]  Moritz Grosse-Wentrup,et al.  Multiclass Common Spatial Patterns and Information Theoretic Feature Extraction , 2008, IEEE Transactions on Biomedical Engineering.

[4]  Patrick Berg,et al.  Common spatial subspace decomposition applied to analysis of brain responses under multiple task conditions: a simulation study , 1999, Clinical Neurophysiology.

[5]  Gary G. Yen,et al.  Cultural-Based Multiobjective Particle Swarm Optimization , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[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]  Arie Yeredor,et al.  A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Jianjun Meng,et al.  Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[9]  Jun Lv,et al.  Common Spatial Pattern and Particle Swarm Optimization for Channel Selection in BCI , 2008, 2008 3rd International Conference on Innovative Computing Information and Control.

[10]  G Pfurtscheller,et al.  Real-time EEG analysis with subject-specific spatial patterns for a brain-computer interface (BCI). , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[11]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.