運用觸覺刺激的腦機介面，干擾認知功能運作的程度較運用視覺或聽覺刺激的腦機介面為低，而在現實世界中有很高的應用價值。先前文獻對於觸覺型腦機介面能否達到與視覺型相當的動作心像類型辨識率尚無結論；此外，運用極少量腦波頻道數是否能達到高動作心像類型辨識率亦屬未知。本研究試圖建立一個腦機介面架構，僅運用四個腦波頻道資訊來進行動作心像類型辨識，然後比較其辨識觸覺和視覺誘發動作心像時之正確率。我們發現應用共同空間型態(common spatial pattern)作為特徵提取器，以及線性區辨分析(linear discriminant analysis)為分類器(classifier)，對觸覺與視覺誘發的左、右手動作心像區辨正確率是相當的；而僅運用C3、C4、Fp1、和Fp2四個頻道的情況下，觸覺與視覺型腦機介面的辨識正確率都可達到85%。本研究之發現可作為未來發展高效能動作心像辨識腦機介面系統之基礎。

Haptic-based Brain Computer Interface (BCI) has great values in real-world applications as it
is less intrusive than visual or auditory based BCI. It is not clear from previous literature
whether haptic-based BCI can achieve equivalent or even better accuracies when applied to the
classification of motor imagery. In addition, it was also not clear whether high classification
accuracy can be achieved in haptic cue based motor imagery BCI with few channels. The
current study sets out to establish a BCI framework using only four channels for motor imagery
classification, and to compare the accuracies between the haptic versus the visual cue based
BCI. We demonstrated that using common spatial pattern (CSP) as feature extractor and linear
discriminant analysis (LDA) algorithm as the classifier, the classification accuracy of the haptic
cue based motor imaginary BCI can reach comparable level as the visual-based one. We also
demonstrated that with only four EEG channels (C3, C4, Fp1, and Fp2), the mean accuracy of
both haptic and visual cue based motor imaginary BCI can reach a high level (~ 85%). The
current findings can serve as the foundation for efficient BCI implementation in motor imagery
classification for future research and real-world applications.

1. Brain–Computer Interfaces: Principles and Practice, Jonathan Wolpaw and Elizabeth Winter Wolpaw, 2012.
2. A brain-computer interface with vibrotactile biofeedback for haptic information, Aniruddha Chatterjee, Vikram Aggarwal, Ander Ramos, Soumyadipta Acharya and Nitish V Thakor Journal of NeuroEngineering and Rehabilitation, 2007.
3. Vibrotactile Feedback for Brain-Computer Interface Operation, Febo Cincotti et al., Computational Intelligence and Neuroscience, 2007.
4. An auditory brain-computer interface (BCI), F. Nijboer, A. Furdea, I. Gunst, J. Mellinger, D. J. McFarland, N. Birbaumer, and A. Kübler, Journal of Neuroscience Methods, 2008.
5. What is feedback in clinical education, J. M. Van de Ridder, K. M. Stokking, W. C. McGaghie, and O. T. J. Ten Gate, 2008.
6. Brain-computer interfaces in medicine, J. J. Shih, D. J. Krusienski, and J. R. Wolpaw, Mayo Clinic Proceedings, 2012.
7. Towards a Spatial Ability Training to Improve Motor Imagery based Brain-Computer Interfaces (MI-BCIs) Performance: a Pilot Study, S. Teillet, F. Lotte, B. N’Kaoua, C. Jeunet, IEEE International Conference on Systems Man and Cybernetics (IEEE SMC), 2016.
8. Common spatial pattern and linear discriminant analysis for motor imagery classification, Shang-Lin Wu ; Chun-Wei Wu ; Nikhil R. Pal ; Chih-Yu Chen ; Shi-An Chen ; Chin-Teng Lin, IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), 2013.
9. Multimodal stimulation for a P300-based BCI, Aloise F., Lasorsa I., Brouwer A. M., Mattia D., Babiloni F., Salinari S., Int. J. Bioelectromagn. 9, 2007.
10. A tactile P300 brain-computer interface, Brouwer AM, van Erp JB, Front Neurosci, 2010.
11. Tactile, visual, and bimodal p300s: could bimodal p300s boost bci performance, Brouwer A.-M., Van Erp J. B. F., Aloise F., Cincotti F., Neuroscience, 2010.
12. Control-display mapping in brain-computer interfaces, Thurlings ME, van Erp JB, Brouwer AM, Blankertz B, Werkhoven P, Ergonomics, 2012.
13. Introducing the tactile speller: an ERP-based brain-computer interface for communication, van der Waal M, Severens M, Geuze J, Desain P J Neural Eng. 2012.
14. Tactually-evoked event-related potentials for bci-based wheelchair control in a virtual environment, Kaufmann T., Herweg A., Kübler A. ,.Proceedings of the Fifth International Brain Computer Interface Meeting, 2003.
15. ERS and ERD Analysis during The Imaginary Movement of Arms, Hong-Gi Yeom and Kwee-Bo Sim, International Conference on Control, Automation and Systems 2008, Oct. 14-17, 2008 in COEX, Seoul, Korea.
16. A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals, Ali Bashashati, Mehrdad Fatourechi, Rabab K Wardand Gary E Birch, J. Neural Eng., 2007.
17. Workshop on BCI signal processing: Feature extraction and translation, McFarland, D.J., Anderson, C.W., Müller, K.R., Schlogl, A., and Krusienski, D.J., IEEE Transactions on Neural Systems and Rehabilition Engineering, 2006.
18. Sensorimotor rhythm-based brain-computer interface (BCI): Feature selection by regression improves performance, McFarland, D.J., and Wolpaw, J.R., IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2005.
19. A review of classification algorithms for EEG-based brain-computer interfaces, Lotte, F., Congedo, M., Leuyer, A., Lmarche, F., and Arnaldi, B., Journal of Neural Engineering, 2007.
20. The use of multiple measurements in taxonomic problems, Fisher, R.A, Annals of Eugenics, 1936.
21. Using space and time to encode vibrotactile information: toward an estimate of the skin’s achievable throughput, Scott D. Novich, David M. Eagleman, Experimental Brain Research, 2015.
22. Machine learning, Tom M. Mitchell, 1997.