The control of a virtual automatic car based on multiple patterns of motor imagery BCI
- 115 Downloads
Multiple degrees of freedom (DOF) commands are required for a brain-actuated virtual automatic car, which makes the brain-computer interface (BCI) control strategy a big challenge. In order to solve the challenging issue, a mixed model of BCI combining P300 potentials and motor imagery had been realized in our previous study. However, compared with single model BCI, more training procedures are needed for the mixed model and more mental workload for users to bear. In the present study, we propose a multiple patterns of motor imagery (MPMI) BCI method, which is based on the traditional two patterns of motor imagery. Our motor imagery BCI approach had been extended to multiple patterns: right-hand motor imagery, left-hand motor imagery, foot motor imagery, and both hands motor imagery resulting in turning right, turning left, acceleration, and deceleration for a virtual automatic car control. Ten healthy subjects participated in online experiments, the experimental results not only show the efficiency of our proposed MPMI-BCI strategy but also indicate that those users can control the virtual automatic car spontaneously and efficiently without any other visual attention. Furthermore, the metric of path length optimality ratio (1.23) is very encouraging and the time optimality ratio (1.28) is especially remarkable.
KeywordsBrain-computer interface Multiple degrees of freedom control Multiple patterns of motor imagery Virtual automatic car
This study was supported by the Technology Development Project of Guangdong Province (No. 2017A010101034), Innovation Projects for Science supported by Department of Education of Guangdong Province (No. 2016KTSCX141), Science Foundation for Young Teachers of Wuyi University (No. 2018td01).
- 5.Serrano JI, del Castillo M, Bayón C, Ramírez O, Lara SL, Martínez-Caballero I, Rocon E (2017) BCI-based facilitation of cortical activity associated to gait onset after single event multi-level surgery in cerebral palsy. In: Brain-Computer interface research. Springer, pp 99–110Google Scholar
- 7.Sirker A, Mamas M, Kwok CS, Kontopantelis E, Ludman P, Hildick-Smith D, Society BCI (2016) Outcomes from selective use of thrombectomy in patients undergoing primary percutaneous coronary intervention for st-segment elevation myocardial infarction: an analysis of the british cardiovascular intervention society/national institute for cardiovascular outcomes research (BCIs-nicor) registry, 2006–2013. J Am Coll Cardiol Intv 9(2):126–134CrossRefGoogle Scholar
- 10.Rebsamen B, Burdet E, Guan C, Zhang H, Teo C, Zeng Q, Ang M, Laugier C (2006) A brain-controlled wheelchair based on p300 and path guidance, in biomedical robotics and biomechatronics, 2006. BioRob. The First IEEE/RAS-EMBS International Conference on IEEE 2006:1101–1106Google Scholar
- 22.Li M, Lin L, Jia S Multi-class imagery eeg recognition based on adaptive subject-based feature extraction and svm-bp classifier. In: Mechatronics and automation (ICMA) 2011 international conference on IEEE 2011, pp 1184–1189Google Scholar
- 24.Dong E, Li C, Li L, Du S, Belkacem AN, Chen C (2017) Classification of multi-class motor imagery with a novel hierarchical svm algorithm for brain–computer interfaces. Med Biolog Eng Comput, 1–10Google Scholar
- 27.Chang C-C, Lin C-J (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3): 27Google Scholar
- 29.Joachims T (1998) Making large-scale svm learning practical, Technical Report, SFB 475: Komplexitätsreduktion in Multivariaten Datenstrukturen. Tech. Rep., Universität DortmundGoogle Scholar
- 30.Allwein EL, Schapire RE, Singer Y (2001) Reducing multiclass to binary: a unifying approach for margin classifiers. J Mach Learn Res 1:113–141Google Scholar