Abstract
Objective. Magnetoencephalography (MEG) based brain–computer interface (BCI) involves a large number of sensors allowing better spatiotemporal resolution for assessing brain activity patterns. There have been many efforts to develop BCI using MEG with high accuracy, though an increase in the number of channels (NoC) means an increase in computational complexity. However, not all sensors necessarily contribute significantly to an increase in classification accuracy (CA) and specifically in the case of MEG-based BCI no channel selection methodology has been performed. Therefore, this study investigates the effect of channel selection on the performance of MEG-based BCI. Approach. MEG data were recorded for two sessions from 15 healthy participants performing motor imagery, cognitive imagery and a mixed imagery task pair using a unique paradigm. Performance of four state-of-the-art channel selection methods (i.e. Class-Correlation, ReliefF, Random Forest, and Infinite Latent Feature Selection were applied across six binary tasks in three different frequency bands) were evaluated in this study on two state-of-the-art features, i.e. bandpower and common spatial pattern (CSP). Main results. All four methods provided a statistically significant increase in CA compared to a baseline method using all gradiometer sensors, i.e. 204 channels with band-power features from alpha (8–12 Hz), beta (13–30 Hz), or broadband (α + β) (8–30 Hz). It is also observed that the alpha frequency band performed better than the beta and broadband frequency bands. The performance of the beta band gave the lowest CA compared with the other two bands. Channel selection improved accuracy irrespective of feature types. Moreover, all the methods reduced the NoC significantly, from 204 to a range of 1–25, using bandpower as a feature and from 15 to 105 for CSP. The optimal channel number also varied not only in each session but also for each participant. Reducing the NoC will help to decrease the computational cost and maintain numerical stability in cases of low trial numbers. Significance. The study showed significant improvement in performance of MEG-BCI with channel selection irrespective of feature type and hence can be successfully applied for BCI applications.
Highlights
Motor disabilities and severe neurological injury require an extra measure in rehabilitation for active and effective environmental interaction
The majority of the available brain–computer interface (BCI) research is focused on EEG, MEG may provide better performance due to its higher signalto-noise ratio (SNR) and spatio-temporal resolution compared to EEG
In reference to figure 4, the random forest (RandF) method performed better than infinite latent feature selection (ILFS) with an increased performance of 1.82% on average across all subjects over six binary classification tasks
Summary
Motor disabilities and severe neurological injury require an extra measure in rehabilitation for active and effective environmental interaction. Motor imagery (MI) practice through brain–computer interface (BCI) has been found to be useful as a therapeutic substitute for standard rehabilitation practices for post-stroke patients [1, 2], and an alternative approach for interaction with the environment [3,4,5,6,7] for people with severe movement disability. Advancements in BCI based technologies have shown promising results in terms of focused interaction for stroke patients [11]. Current BCI systems may use magnetoencephalography (MEG), electroencephalography (EEG), functional magnetic resonance imaging or electrocorticography approaches for mapping brain responses [7, 12,13,14,15,16,17]. Unlike EEG, MEG sensors are placed in a dedicated helmet rather than physically placed on subjects’ scalps resulting in significant signal attenuation [18]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
