Reducing execution time for real-time motor imagery based BCI systems

Selim S. ; Tantawi M. ; Shedeed H. ; Badr A. 


Abstract


Brain Computer Interface (BCI) systems based on electroencephalography (EEG) has introduced a new communication method for people with severe motor disabilities. One of the main challenges of Motor Imagery (MI) is to develop a real-time BCI system. Using complex classification techniques to enhance the accuracy of the system may cause a remarkable delay of real-time systems. This paper aims to achieve high accuracy with low computational cost. Two public datasets (BCIC III IVa and BCIC IV IIa) were used in this study; to check the robustness of the proposed approach. Dimension reduction of input signal has been done by channel selection and extracting features using Root Mean Square (RMS). The extracted features have been examined with four different classifiers. Experimental results showed that using Least Squares classifier gives best results, compared to other classifiers, with minimum computational time.


Other data

Issue Date 1-Jan-2017
Publisher © Springer International Publishing AG 2017.
Journal Advances in Intelligent Systems and Computing 
URI http://research.asu.edu.eg/123456789/138
ISBN 9783319483078
DOI http://api.elsevier.com/content/abstract/scopus_id/84994514906
555
533
10.1007/978-3-319-48308-5_53


Recommend this item

CORE Recommender
3
Citations

11
Views


Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.