CC BY
22
Section BRAIN-COMPUTER INTERFACES, COGNITIVE NAVIGATION WORKSHOP AND NEUROENGINEERING
Rapid SSVEP Mindspelling Achieved with Beamforming
Benjamin Wittevrongel and Marc M. Van Hulle*
Laboratory for Neuro- and Psychophysiology, KU Leuven, Leuven, Belgium. * Presenting e-mail: [email protected]
In brain-computer interfacing (BCI) based on steady-state visual evoked potentials (SSVEPs), the number of selectable targets is rather limited when each target has its own stimulation frequency. One way to remedy this is by combining frequency- and phase-coding. We introduce a new multivariate spatiotemporal filter, based on Linearly Constraint Minimum Variance (LCMV) beamforming (van Vliet et al., 2015), for discriminating between frequency-phase coded targets more accurately, even when using short signal lengths, than with (extended) Canonical Correlation Analysis (CCA) that is traditionally posited for this stimulation paradigm (Nakanishi et al., 2014). Our results show that with our new decoding scheme and spatiotemporal beamforming, accurate spelling can be achieved even in an online setting.
Acknowledgements
BW is supported by the Agency for Innovation by Science and Technology in Flanders (IWT). MMVH is supported by research grants received from the program Financing program (PFV/10/008), an interdisciplinary research project (IDO/12/007) and an industrial research fund project (IOF/HB/12/O21) of the KU Leuven, the Belgian Fund for Scientific Research Flanders (G088314N, G0A0914N), the Interuniversity Attraction Poles Programme Belgian Science Policy (IUAP P7/11), the Flemish Regional Ministry of Education (Belgium) (GOA 10/019), and the Hercules Foundation (AKUL 043).
References
1. M. van Vliet, N. Chumerin, S. De Deyne, J.R. Wiersema, W. Fias, G. Storms, and M.M. Van Hulle, "Single-trial erp component analysis using a spatio-temporal lcmv beamformer," Biomedical Engineering, IEEE Transactions on, vol. PP, no. 99, pp. 1-1, 2015.A. One, B. Two, and C. Three, Phys. Rev., 1972, 8(3), 555-566.
2. Nakanishi M., Wang Y., Wang Y.T., Mitsukura Y., Jung T.P. A high-speed brain speller using steady-state visual evoked potentials. International journal of neural systems. 2014;24(06):1450019.
The Control Human Phantom Fingers by Means of P300 Brain-Computer Interface for Neurorehabilitation
A.Ya. Kaplan1,2 *, D.D.Zhigulskaya1, D.A.Kirjanov1
1 Laboratory for Neurophysiology and Nero-Computer Interfaces, Faculty of Biology, Lomonosov Moscow State University, Moscow;
2 Lobachevsky National Research State University of Nizhny Novgorod, Nizhny Novgorod * Presenting e-mail: [email protected]
Aims of the study
Motor imagery (MI) that triggers restructuring of the motor act plan in neuronal networks can be as effective for the restoration of impaired motor coordination as the actual implementation of the movement. However, despite the seeming simplicity of MI, whether it is effective in triggering cortical restructuring depends on mental effort intensity, stability and direction. The feedback loop can be provided by brain-computer interface (BCI) technologies based on eEg recording and mu-rhythm depression that allow for detecting mental representations of movements and transforming those events into commands for controlling the external objects. Using this skill during training sessions is an effective trigger for adaptive plasticity processes in the corresponding brain structures [1]. The weakness of this approach is the extremely low level of differentiation of mental movement representations in relation to their subsequent BCI-based identification.
OM&P
Spatiotemporal
Section BRAIN-COMPUTER INTERFACES, COGNITIVE NAVIGATION WORKSHOP AND NEUROENGINEERING
Only 2-3 motor images can be reliably identified by BCI on the basis of motor imagery. It is not enough in case there is a necessity to establish several feedback channels for mental rehearsal of fine motor skills, such as movements of individual fingers, which are the hardest to restore. At the same time, there is a BCI technology that uses EEG for the reliable detection of human focus of attention on external screen characters and allows for further creation of a library that contains no less than 36 commands [2]. Detection of the attention focus is based on EEG responses to short flashes of external objects, such as symbols on the screen; response to a target stimulus is identified on the basis of specific response parameters, a P300 wave in particular. Still, BCI-P300 seems to have some prospects for being used in rehabilitation as a communicator only, such as for spelling.
In this work we test the hypothesis that BCI-P300 can be used in a non-standard manner: as a basis for a training simulator for improving fine motor skills (of fingers) with a multichannel feedback. For this simulator, the anthropomorphic hand phantom with movable fingers can be used as an actuator. We speculate that using a BCI-P300 system proposed in this work, an individual will be able to control phantom finger flexion by focusing his attention on the fingers. The onset of finger movement will indicate the sufficient intensity of mental effort aimed at focusing attention on the process.
Methods
The study enrolled 12 volunteers (18-25 years of age). Above the right arm of the subject covered with non-transparent fabric, the anthropomorphic hand was placed, with movable fingers connected to servo-motors by means of flexible cords. Light markers (LEDs) were attached to the distal phalanx of each phantom finger. Turning them on and off was a visual stimulus for event-related potentials (ERPs) recorded by EEG (NVX52,MKS, Russia). To identify ERPs associated with target stimuli, i.e., flashes of the light markers on the phantom finger that the subject's attention was focused on, Fisher linear classifier based on Fisher linear discriminant analysis (LDA) was used; its output was transformed into a finger-flexion command for the phantom if the preset threshold was exceeded. During the experimental session, a randomized sequence of flashes for each phantom finger was presented to the subject necessary to perform one command, i.e., to flex one phantom finger that the subject's attention was drawn to by flashes. Each command was preceded by instructing the subject on what phantom finger had to be chosen. Every subject had 20 experimental trials spaced by small breaks; the results of the trials were used to assess how effectively the subject operated the hand phantom. Immediately before the experimental session, the classifier was trained using non-random sampling of target and non-target ERPs. The effectiveness of phantom finger control was assessed based on control accuracy parameters, namely, the number of right, wrong or absent phantom finger flexions while focusing the attention on a certain phantom finger.
Results
It was shown subjects rarely fail to select the target finger for flexion. In average, there are no more than 1.5 errors in 20 trials. But in a greater number of cases (5-6 depending on the operating mode), subjects fail to initiate flexion of any finger leaving the phantom hand motionless. Wilcoxon test showed significant differences (p<0.05) when comparing the number of type 1 and type 2 errors for each experimental mode. Setting a non-target finger in motion is an error possibly related to the unstable attention focus, as a result of which attention is drawn to the non-target finger, and the latter is wrongly detected as a flexion target.
Conclusions
The BCI-P300 technology can enable generation of commands for mental control of fingers of the human hand phantom with reliability of no less than 69%, which is sufficient to develop a fine motor skills neurosimulator. The majority of the BCI-P300 operator's errors in controlling the fingers of the human hand phantom are associated with insufficient focus on the signals of the light markers placed on phantom fingers, which necessitates the improvement of the stimulus media.
Acknowledgements
This study was partially supported by funding from the Skolkovo Foundation (project 1110034) and from Russian Science Foundation (15-19-20053).
References
1. Mokienko OA, Chervyakov AV, Kulikova SN, Bobrov PD, Chernikova LA, Frolov AA, et al. Increased motor cortex excitability during motor imagery in brain-computer interface trained subjects. Front Comput Neurosci. 2013 Nov 22; 7: 168.
2. Kaplan AY, Shishkin SL, Ganin IP, Basyul IA, Zhigalov AY. Adapting the P300-based brain-computer interface for gaming: a review. IEEE Trans Comput Intell AI Games. 2013; 5 (2): 141-9.
OM&P
