Channel selection by genetic algorithms for classifying single-trial ECoG during motor imagery

Abstract

The classification performance of a brain-computer interface (BCI) depends largely on the methods of data recording and feature extraction. The electrocorticogram (ECoG)-based BCIs are a BCI modality that has the potential to achieve high classification accuracy. This paper proposes a new algorithm for classifying single-trial ECoG during motor imagery. The optimal channel subsets are first selected by genetic algorithms from multi-channel ECoG recordings, then the power features are extracted by common spatial pattern (CSP), and finally Fisher discriminant analysis (FDA) is used for classification. The algorithm is applied to Data set I of BCI Competition III and the classification accuracy of 90% is achieved on test set by using only seven channels.

Classification of contralateral and ipsilateral finger movements for electrocorticographic brain-computer interfaces

“…Because of these factors, we and others have proposed ECoG as an ideal target for brain-machine computer (BCI) applications 14,16,18,21,28,30,31,33 and have shown how advanced mathematical methods allow for fast and accurate isolation of BCI control signals without requiring prior knowledge of salient signal features: particular electrodes and frequencies for BCI control do not need to be determined ahead Classification of contralateral and ipsilateral finger movements for electrocorticographic brain-computer interfaces of time but can be automatically tuned to the individual's ECoG signals. 35,36 The ability to decode information about movements from ECoG has been well demonstrated. 6,8,9,11,13,14,19,22,25,27 One concern is whether these potential control signals for BCI are still present in an individual with a damaged brain.…”

Channel and Feature Selection for a Motor Imagery-Based BCI System Using Multilevel Particle Swarm Optimization

“…By using only three features, 93% accuracy can be achieved, but the subset of its features will increase algorithm complexity. Wei et al [24] selected the optimal channel through the genetic algorithm, SF: selected features; ACC: accuracy; TRT: training time; TTT: total training time of channel selection and feature selection; TET: test time; SEN: sensitivity; SPE: specificity; PRE: precision.…”

Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

“…The reduction of the dimension of neural feature representations is mainly performed in offline or online motor BCI studies by means of projection methods, such as the principal component analysis and its variants (Devulapalli, 1996 ; Wu et al, 2003b ; Kim S.-P. et al, 2006 ; Aggarwal et al, 2008 ; Ke and Li, 2009 ; Wang W. et al, 2009 ; Argunşah and Çetin, 2010 ; Suk and Lee, 2010 ; Bhattacharyya et al, 2011 ; Kao et al, 2013 , 2017 ) or by means of feature selection methods, such as stepwise forward (Brunner et al, 2007 ; Liang and Bougrain, 2012 ; Wang et al, 2012 ; Hotson et al, 2014 ) or forward-backward (McFarland et al, 2010 ) selection procedures, LASSO-based sparse modeling methods (Least Absolute Shrinkage and Selection Operator) (Fazli et al, 2011 ; Kelly et al, 2012 ; Wang et al, 2015 ), so-called filter methods (Schalk et al, 2007 ; Spüler et al, 2016 ), genetic algorithms (Flotzinger et al, 1994 ; Graimann et al, 2004 ; Wei et al, 2006 ; Boostani et al, 2007 ; Fatourechi et al, 2007 ; Wei and Tu, 2008 ) or alternative approaches such as distinctive sensitive learning vector quantization (Flotzinger et al, 1994 ).…”