Kodama T, Shimizu K, Makino S, Rutkowski TM. Full–body Tactile P300–based Brain–computer Interface Accuracy Refinement. In: Proceedings of the International Conference on Bio-engineering for Smart Technologies (BioSMART 2016). Dubai, UAE: IEEE Press; 2016. p. 20-23.

1. 1
Takumi Kodama , Kensuke Shimizu ,
Shoji Makino and Tomasz M. Rutkowski
Full–body Tactile
P300–based
Brain–computer Interface
Accuracy Refinement
@bioSMART conference 2016
1 1
1 2, 3, 4
1 2
3 4
Life Science Center of TARA, University of Tsukuba, The University of Tokyo,
Saitama Institute of Technology, RIKEN Brain Science Institute

2. 1: Introduction - What’s BCI?
● Brain Computer Interface (BCI)
○ Neurotechnology
○ Exploits user intention ONLY using brainwaves
2

3. 1: Introduction - ALS Patients
● Amyotrophic lateral sclerosis (ALS) patients
○ Have difficulty to move their muscle by themselves
○ BCI could be a communicating tool for them
3
!
…
…

4. ● Tactile (Touch-based) P300-based BCI paradigm
○ P300 responses were evoked by external (tactile) stimuli
○ Predict user’s intentions by decoding P300 responses
1: Introduction - Research Approach
41. Stimulate touch sensories 2. Classify brain response
A
B
A
B
3. Predict user intention
92.0% 43.3%
A B
Target
Non-Target
P300 brainwave response

5. ● Full-body Tactile P300-based BCI (fbBCI) [1]
○ Applies six vibrotactile stimulus patterns to user’s back
○ User can use fbBCI while lying down and interacting
using a whole body surface
1: Introduction - Our Method
5[1] Kodama T, Shimizu K, Rutkowski TM. Full Body Spatial Tactile BCI for Direct Brain-robot Control. In: Proceedings of the Sixth International
Brain-Computer Interface Meeting. Asilomar Conference Center, Pacific Grove, CA USA: Verlag der Technischen Universitaet Graz; 2016. p. 68.

6. 1: Introduction - Demonstration
6
https://www.youtube.com/watch?v=sn6OEBBKsPQ

7. ● P300 responses were confirmed (> 4 μV) in each channel
1: Introduction - fbBCI results (1)
7
Target
Non-Target

8. ● Problem: Low online classification accuracies
○ SWLDA : 53.67 % (10 users average)
1: Introduction - fbBCI results (2)
8

9. ● To improve the fbBCI classification accuracy
● To reconfirm the validity of fbBCI modality
1: Introduction - Research Purpose
9

10. ● Test several signal preprocessing combinations ①
○ Downsampling
○ Epoch averaging
● Classify with three different machine learning methods ②
○ SWLDA
○ Linear SVM
○ Non-linear SVM (Gaussian kernel)
2: Method - Conditions
10
CommandBrainwave
① ②

11. 2: Method - Signal Acquisition
11
● Event related potential (ERP)
○ captures 800 ms after an onset of vibrotactile stimulus
○ next converted to a feature vector using EEG potential
ex.)
fs = 512 [Hz]
ERPinterval = 800 [ms] = 0.8 [sec]
Vlength = ceil(512・0.8) = 410
Vlength
VCh○○
p[0]
…
p[Vlength - 1]
Vlength = ceil( fs・ERPinterval)
where fs [Hz] , ERPinterval [sec]
Ch○○

12. 2: Method - Signal Preprocessing(1)
12
● Downsampling (nd)
○ ERPs were decimated by
4 (128 Hz), 16 (32 Hz) or kept
intact (512 Hz)
○ To reduce vector length Vlength
nd = 4 (128 Hz) nd = 16 (32 Hz)
Ch○○ Ch○○

13. 13
● Epoch averaging (ne)
○ ERPs were averaged using 5, 10
ERPs or no averaging
○ To cancel background noise
ne = 1 ne = 10
Ch○○ Ch○○
2: Method - Signal Preprocessing(2)

14. ● Concatenating all feature vectors
2: Method - Feature Extraction
ex.)
fs = 128 [Hz] (nd = 4)
Vlength = ceil(128・0.8) = 103
14
…
Vlength
VCz …
Vlength
VPz …
Vlength
VCP6
…
…
… … ……V
ex.) VlengthALL = Vlength・8 = 103・8 = 824
VlengthALL
…
Ch1 Ch2 Ch8

15. ● Machine learning methods
○ SWLDA
○ Linear SVM
… K(u,v’) = u v’
○ Non-linear SVM (Gaussian)
… K(u,v’) = exp(-γ||u-v|| )
γ = 1/VlengthALL , c = 1
2: Method - Classification (1)
15
T
2

16. ● Training the classifier
2: Method - Classification (2)
16
VT1
VT2
VlengthALL VlengthALL
VN1
VN2
VTmax
・
・
・
・
・
・
VNmax
・
・
・
VTmax = 60 / ne VNmax = 300 / ne
Classifier (2cls)
Non-TargetTarget

17. ● Training the classifier
2: Method - Classification (2)
17
VT1
VT2
VlengthALL VlengthALL
VN1
VN2
Classifier (2cls)
VTmax
・
・
・
・
・
・
VNmax
VTmax = 60 / ne VNmax = 60 / ne
Random choose
as many as Tmax
}
Non-TargetTarget

18. ● Evaluation with the trained classifier
○ Same nd and ne were applied
2: Method - Classification (3)
18
VT1
VlengthALL
・
・
VTmax = 10 / ne
Target? or
Non-Target? Classifier (2cls)
Test data

19. ● SWLDA classification accuracies
○ BEST: 57.48 % (nd = 4, ne = 1)
3: Results - SWLDA
19
Signal decimation (nd)

20. ● Linear SVM classification accuracies
○ BEST: 58.5 % (nd = 16, ne = 10)
3: Results - Linear SVM
20
Signal decimation (nd)

21. ● Non-linear SVM classification accuracies
○ BEST: 59.83 % (nd = 4, ne = 1)
3: Results - Non-linear SVM
21
Signal decimation (nd)

22. 4: Discussion and conclusions
22
● fbBCI classification accuracy has been improved
○ Both nd and ne combinations were tested
○ 53.67 % in previous reported results
⇒ 59.83 % by non-linear SVM (nd = 4, ne = 1)
○ 58.5 % by linear SVM and 57.48 % by SWLDA
● The potential validity of fbBCI modality was reconfirmed
○ Expect to improve a QoL for ALS patients
● However, more analyses would be required
○ Only 10 healthy users of fbBCI paradigm
○ Need higher accuracies in case of a practical application

23. 23
Many thanks for your attention!