Abstract
A right-hand motor imagery based brain-computer interface is proposed in this work. Such a system requires the identification of different brain states and their classification. Brain signals recorded by electroencephalography are naturally contaminated by various noises and interferences. Ocular artifact removal is performed by implementing an auto-matic method “Kmeans-ICA” which does not require a reference channel. This method starts by decomposing EEG signals into Independent Components; artefactual ones are then identified using Kmeans clustering, a non-supervised machine learning technique. After signal preprocessing, a Brain computer interface system is implemented; physiologically interpretable features extracting the wavelet-coherence, the wavelet-phase locking value and band power are computed and introduced into a statistical test to check for a significant difference between relaxed and motor imagery states. Features which pass the test are conserved and used for classification. Leave One Out Cross Validation is performed to evaluate the performance of the classifier. Two types of classifiers are compared: a Linear Discriminant Analysis and a Support Vector Machine. Using a Linear Discriminant Analysis, classification accuracy improved from 66% to 88.10% after ocular artifacts removal using Kmeans-ICA. The proposed methodology outperformed state of art feature extraction methods, namely, the mu rhythm band power.
Highlights
The first Brain-Computer Interface (BCI) based system was proposed by Vidal in 1973 hundred years after the discovery of brain electrical activity [1]
Results can be divided into two main parts: the first describes the performance of the ocular artifact rejection method; a case is considered for visualization purposes and quantitative evaluation methods are presented
Results of the Statistical Test In order to quantify the discriminative power of these features, significance difference has been tested between relax and motor imagery states using the t-test, a statistical significance test applied to small data sets
Summary
The first Brain-Computer Interface (BCI) based system was proposed by Vidal in 1973 hundred years after the discovery of brain electrical activity [1]. Many researches have been conducted in this field; the traditional approach is a manual identification of artefactual Independent Components (ICs) by interpreting activation time series, scalp topographies, and frequency distribution This approach may show usable for offline EEG preprocessing and analysis, it is not suitable for online BCI applications [11]. “Kmeans-ICA”, a fully automatic filtering method based on ICA was implemented to remove overlapping ocular artifacts in a BCI framework. This method extracts simple features from ICs’ time series and does not require adding an EOG channel. The average correlation of each IC with prefrontal electrodes (most contaminated by EOG noise), the maximum value of each IC, and the ratio between the peak amplitude and the variance of each IC are used as inputs to a non-supervised clustering algorithm [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
