Improved SFFS method for channel selection in motor imagery based BCI

BackgroundMultichannels used in brain-computer interface (BCI) systems contain redundant information and cause inconvenience for practical application. Channel selection can enhance the performance of BCI by removing task-irrelevant and redundant channels. Sequential floating forward selection (SFFS) is an intelligent search algorithm and is considered one of the best feature selection methods in the literature. However, SFFS is time consuming when the number of features is large. MethodIn this study, the SFFS method was improved to select channels for the common spatial pattern (CSP) in motor imagery (MI)-based BCI. Based on the distribution of channels in the cerebral cortex, the adjacent channels would be treated as one feature for selection. Thus, in the search process, the improved SFFS could select or remove several channels in each iteration and reduce the total computation time. ResultsThe improved SFFS yielded significantly better performance than using all channels (p<0.01) and support vector machine recursive feature elimination method (p<0.05). The computation time of the proposed method was significantly reduced (p<0.005) compared with the original SFFS method. ConclusionsThis study improved the SFFS method to select channels for CSP in MI-based BCI. The improved SFFS method could significantly reduce computation time compared with the original SFFS without compromising the classification accuracy. This study provided a way to optimize electroencephalogram channels, which combined the distribution of channels and the intelligent selection method (SFFS). Improvements were mainly in the perspective of reducing computation time, which leads to convenience in the practical application of BCI systems.

[1]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[2]  Dennis J. McFarland,et al.  Brain–computer interfaces for communication and control , 2002, Clinical Neurophysiology.

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

[4]  Jonathan E. Gale,et al.  High-Threshold Mechanosensitive Ion Channels Blocked by a Novel Conopeptide Mediate Pressure-Evoked Pain , 2007, PloS one.

[5]  Xingyu Wang,et al.  An adaptive P300-based control system , 2011, Journal of neural engineering.

[6]  Yuanqing Li,et al.  Classifying Motor Imagery EEG Signals by Iterative Channel Elimination according to Compound Weight , 2010, AICI.

[7]  G Pfurtscheller,et al.  Frequency component selection for an EEG-based brain to computer interface. , 1999, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[8]  Gary E. Birch,et al.  Sparse spatial filter optimization for EEG channel reduction in brain-computer interface , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Ahmed H. Tewfik,et al.  Greedy solutions for the construction of sparse spatial and spatio-spectral filters in brain computer interface applications , 2013, Neurocomputing.

[10]  Klaus-Robert Müller,et al.  The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects , 2008, IEEE Transactions on Biomedical Engineering.

[11]  Reza Boostani,et al.  An efficient hybrid linear and kernel CSP approach for EEG feature extraction , 2009, Neurocomputing.

[12]  Ruimin Wang,et al.  Classification of Four-Class Motor Imagery Employing Single-Channel Electroencephalography , 2014, PloS one.

[13]  Misha Pavel,et al.  Channel Selection and Feature Projection for Cognitive Load Estimation Using Ambulatory EEG , 2007, Comput. Intell. Neurosci..

[14]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[15]  Cuntai Guan,et al.  Selection of effective EEG channels in brain computer interfaces based on inconsistencies of classifiers , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Rami Saab,et al.  An Auditory-Tactile Visual Saccade-Independent P300 Brain-Computer Interface , 2016, Int. J. Neural Syst..

[17]  Yonghong Peng,et al.  A novel feature selection approach for biomedical data classification , 2010, J. Biomed. Informatics.

[18]  Ian Daly,et al.  Single tap identification for fast BCI control , 2011, Cognitive Neurodynamics.

[19]  Javier Gomez-Pilar,et al.  Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces , 2015, Neurocomputing.

[20]  Chong Liu,et al.  Classification of ECoG motor imagery tasks based on CSP and SVM , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[21]  Yijun Wang,et al.  Common Spatial Pattern Method for Channel Selelction in Motor Imagery Based Brain-computer Interface , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[22]  A. Cichocki,et al.  An optimized ERP brain–computer interface based on facial expression changes , 2014, Journal of neural engineering.

[23]  Jianjun Meng,et al.  Model based generalization analysis of common spatial pattern in brain computer interfaces , 2010, Cognitive Neurodynamics.

[24]  Chin-Teng Lin,et al.  An EEG-Based Brain-Computer Interface for Dual Task Driving Detection , 2011, ICONIP.

[25]  A. Kübler,et al.  Face stimuli effectively prevent brain–computer interface inefficiency in patients with neurodegenerative disease , 2013, Clinical Neurophysiology.

[26]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[27]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[28]  Cuntai Guan,et al.  Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI , 2011, IEEE Transactions on Biomedical Engineering.

[29]  Clemens Brunner,et al.  Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks , 2006, NeuroImage.

[30]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[31]  S. G. Ponnambalam,et al.  Multi-objective genetic algorithm as channel selection method for P300 and motor imagery data set , 2015, Neurocomputing.

[32]  D. Yao,et al.  The graph theoretical analysis of the SSVEP harmonic response networks , 2015, Cognitive Neurodynamics.

[33]  Ester Cerin,et al.  Understanding Neighborhood Environment Related to Hong Kong Children’s Physical Activity: A Qualitative Study Using Nominal Group Technique , 2014, PloS one.

[34]  Francisco Velasco-Álvarez,et al.  Audio-cued motor imagery-based brain-computer interface: Navigation through virtual and real environments , 2013, Neurocomputing.

[35]  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.

[36]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[37]  Bernhard Schölkopf,et al.  Support vector channel selection in BCI , 2004, IEEE Transactions on Biomedical Engineering.

[38]  Yuanqing Li,et al.  Surfing the internet with a BCI mouse , 2012, Journal of neural engineering.

[39]  G Pfurtscheller,et al.  Graphical display and statistical evaluation of event-related desynchronization (ERD). , 1977, Electroencephalography and clinical neurophysiology.

[40]  Tian Lan,et al.  Salient EEG Channel Selection in Brain Computer Interfaces by Mutual Information Maximization , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[41]  Andrés Marino Álvarez-Meza,et al.  Time-series discrimination using feature relevance analysis in motor imagery classification , 2015, Neurocomputing.

[42]  Xingyu Wang,et al.  A P300 Brain-Computer Interface Based on a Modification of the Mismatch Negativity Paradigm , 2015, Int. J. Neural Syst..

[43]  Xingyu Wang,et al.  A comparison of three electrode channels selection methods applied to SSVEP BCI , 2011, 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI).

[44]  K. Müller,et al.  Single Trial Classification of Motor Imagination Using 6 Dry EEG Electrodes , 2007, PloS one.

[45]  Xingyu Wang,et al.  Optimizing spatial patterns with sparse filter bands for motor-imagery based brain–computer interface , 2015, Journal of Neuroscience Methods.

[46]  A. Cichocki,et al.  A survey of the dummy face and human face stimuli used in BCI paradigm , 2015, Journal of Neuroscience Methods.

[47]  A. Al-Ani,et al.  Effect of Feature and Channel Selection on EEG Classification , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[48]  G. Pfurtscheller.  Event-related synchronization (ERS): an electrophysiological correlate of cortical areas at rest. , 1992, Electroencephalography and Clinical Neurophysiology.

[49]  Jianjun Meng,et al.  Optimizing spatial spectral patterns jointly with channel configuration for brain-computer interface , 2013, Neurocomputing.

[50]  Feng Wan,et al.  Adaptive time-window length based on online performance measurement in SSVEP-based BCIs , 2015, Neurocomputing.

[51]  Yongyi Yang,et al.  Improving SVM classifier with prior knowledge in microcalcification detection1 , 2012, 2012 19th IEEE International Conference on Image Processing.

[52]  Cuntai Guan,et al.  Robust filter bank common spatial pattern (RFBCSP) in motor-imagery-based brain-computer interface , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

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

[54]  Yuanqing Li,et al.  Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG , 2013, Neurocomputing.

[55]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[56]  Yuanqing Li,et al.  A comparison study of two P300 speller paradigms for brain–computer interface , 2013, Cognitive Neurodynamics.