Long-term paired sensory stimulation training for improved motor imagery BCI performance via pavlovian conditioning theory

In this work, paired sensory stimulation training via pavlovian conditioning (PSSPC) was proposed to improve motor imagery BCI performance, especially targeted in those poor performing BCI users. Motor imagery task was paired with the sensory stimulus to establish the conditioned responses through the long-term classic conditioning training. Three poor performing subjects were recruited to participate the PSSPC experiment lasting for about one month in eight sessions. R2 contrast image have shown that the discriminative brain pattern was emerged out in the sensorimotor area of the brain after several sessions training. In addition, up to 80% BCI performance was achieve to some subjects, and it has also shown that learning was evolved in the PSSPC training, complementary to the feedback based training (also termed operant conditioning). The PSSPC methodology has the potential in improving those poor performing BCI subjects, and laid the potential to guide the cortical plastic changes for those with motor impairments.

[1]  H. Flor,et al.  A spelling device for the paralysed , 1999, Nature.

[2]  J. Wolpaw,et al.  Brain–computer interfaces in neurological rehabilitation , 2008, The Lancet Neurology.

[3]  L. R. Quitadamo,et al.  Investigating the effects of a sensorimotor rhythm-based BCI training on the cortical activity elicited by mental imagery , 2014, Journal of neural engineering.

[4]  C. Neuper,et al.  Sensorimotor rhythm-based brain–computer interface training: the impact on motor cortical responsiveness , 2011, Journal of neural engineering.

[5]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[6]  Vera Kaiser,et al.  Cortical effects of user training in a motor imagery based brain–computer interface measured by fNIRS and EEG , 2014, NeuroImage.

[7]  Xiangyang Zhu,et al.  Enhanced motor imagery based brain-computer interface via unilateral wrist vibrotactile stimulation , 2013, 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER).

[8]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[9]  Thomas H. Wonnacott,et al.  Introductory Statistics , 2007, Technometrics.

[10]  C. A. Ruf,et al.  Brain communication in the locked-in state. , 2013, Brain : a journal of neurology.

[11]  Clemens Brunner,et al.  Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks , 2006, NeuroImage.

[12]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[13]  D. Whitteridge Lectures on Conditioned Reflexes , 1942, Nature.

[14]  G. Pfurtscheller,et al.  Motor imagery and action observation: Modulation of sensorimotor brain rhythms during mental control of a brain–computer interface , 2009, Clinical Neurophysiology.

[15]  Benjamin Blankertz,et al.  Towards a Cure for BCI Illiteracy , 2009, Brain Topography.

[16]  Jianjun Meng,et al.  Mechanical vibrotactile stimulation effect in motor imagery based brain-computer interface , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).