Application of Swarm Intelligence Optimization in EEG Analysis

In order to improve time efficiency of brain-computer interface (BCI), swarm intelligence optimization (SIO) based algorithms were used to analyze electroencephalogram (EEG). Artificial fish swarm algorithm (AFSA), a SIO algorithm, initiated several points in feasible domain of de-mixing matrix w, and parallel searched. These mechanism made the algorithm iterate fasterly. Ulteriorly, the introduction of chaos searching enhanced convergence precision. The experiments ran on real EEG data for ocular artifacts removal and P300 extraction respectively. PIs were all less than 0.08 and iteration numbers were superior than classic algorithm. These results show SIO based algorithms can effectively reduce computation time for EEG based BCI with the operation precision remaining unimpaired.

[1]  Touradj Ebrahimi,et al.  An efficient P300-based brain–computer interface for disabled subjects , 2008, Journal of Neuroscience Methods.

[2]  Zhang Zhi-wei.  Improved Higher Order Convergent FastICA Algorithm , 2011 .

[3]  F. La Foresta,et al.  Automatic Artifact Rejection From Multichannel Scalp EEG by Wavelet ICA , 2012, IEEE Sensors Journal.

[4]  M. Bala Krishna,et al.  Swarm intelligence-based topology maintenance protocol for wireless sensor networks , 2011, IET Wirel. Sens. Syst..

[5]  Yun Q. Shi,et al.  Detecting Covert Channels in Computer Networks Based on Chaos Theory , 2013, IEEE Transactions on Information Forensics and Security.

[6]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[7]  Lester Ingber,et al.  Statistical mechanics of neocortical interactions: Training and testing canonical momenta indicators of EEG , 1998, physics/0001053.

[8]  V. Salai Selvam,et al.  Brain tumor detection using scalp eeg with modified Wavelet-ICA and multi layer feed forward neural network , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[10]  Heung-Il Suk,et al.  A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.