Classification of EEG-Based Brain–Computer Interfaces
This chapter demonstrates the development of a brain computer interface (BCI) decision support system for controlling the movement of a wheelchair for neurologically disabled patients using their Electroencephalography (EEG). The subject was able to imagine his/her hand movements during EEG experiment which made EEG oscillations in the signal that could be classified by BCI. The BCI will translate the patient’s thoughts into simple wheelchair commands such as “go” and “stop”. EEG signals are recorded using 59 scalp electrodes. The acquired signals are artifacts contaminated. These artifacts were removed using blind source separation (BSS) by independent component analysis (ICA) to get artifact-free EEG signal from which certain features are extracted by applying discrete wavelet transformation (DWT). The extracted features were reduced in dimensionality using principal component analysis (PCA). The reduced features were fed to neural networks classifier yielding classification accuracy greater than 95 %.
KeywordsElectroencephalography (EEG) Brain computer interface (BCI) Decision support system (DSS) Principal component analysis (PCA) Independent component analysis (ICA) Discrete wavelet transformation (DWT) Artificial neural network (ANN) Feature extraction Classification Computational Intelligence (CI) Machine learning
The research of Valentina Emilia Balas was supported by the Bilateral Cooperation Research Project between Bulgaria-Romania (2010-2012) entitled “Electronic Health Records for the Next Generation Medical Decision Support in Romanian and Bulgarian National Healthcare Systems”, NextGenElectroMedSupport.
- 4.Kauhanen, L., Jylanki, P., Janne, L.J. et al.: EEG-based brain-computer interface for tetraplegics. Comput. Intell. Neurosc. l, 11, Article ID 23864, (2007). doi: 10.1155/2007/23864
- 8.Bashashati, A., Fatourechi, M., Ward, R.K., Birch, G.E.: A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals. J Neural Eng. 4(2), R32–57 (2007)Google Scholar
- 14.del Millán, J., Mouriño, J.R: Asynchronous BCI and local neural classifiers: An overview of the adaptive brain interface project. IEEE Trans. Neural Syst. Rehabil. Eng. 11(2), 159–61 (2003)Google Scholar
- 16.Makeig, S., Bell, A., Jung, T.P., Sejnowski, T.J.: Independent component analysis of electroencephalographic data. In: Touretzky, D., Mozer, M., Hasselmo, M. (eds.) Advances in neural information processing systems, pp. 145–151 (1996)Google Scholar
- 22.Aydemir, O., Kayikcioglu, T.: Wavelet transform based classification o invasive brain computer interface data. Radioengineering 20(1), 31–38 (2011)Google Scholar
- 24.Lakany, H., Conway, B.A.: Classification of wrist movements using EEG-based wavelets features. In: Proceedings of 27th IEEE EMBS Annual Conference, China, pp. 5404–5407 (2005)Google Scholar
- 25.Dong, S.C., Amato, V., Murino, V.: Wavelet-based processing of EEG data for brain-computer interfaces. In: Proceedings of IEEE Computer Society Conference, USA, pp. 74–74 (2005)Google Scholar
- 26.Yong, Y.P.A., Hurley, N.J., Silvestre, G.C.M.: Single trial EEG classification for brain-computer interface using wavelet decomposition. In: Procedings of EUSIPCO 2005, Eurasip, Antalya, Turkey, (2005)Google Scholar
- 28.Rumelhart, D.E., Durbin, R., Golden, R., Chauvin, Y.: Backpropagation: Theory, Architectures, and Applications, Hillsdale, Lawrence Erlbaum Association, New Jersey, pp.1–34 (1995)Google Scholar
- 29.Nicolaou, N., Nasuto, S.J.: Temporal independent component analysis for automatic artifact removal from EEG. In: Proceedings of 2nd International Conference on Medical Signal and Information Signal Processing, Sliema, Malta (2004)Google Scholar
- 31.Ramoser, H., Müller-Gerking, J., Pfurtscheller, G.: Designing optimal spatial filters for single trial EEG during imagined movement. IEEE Trans. Rehab. Eng. 8(4), (2000)Google Scholar
- 32.He, S.L., Xiaorong, G., Fusheng, Y., Shangkai, G.: Imagined hand movement identification based on spatio-temporak pattern recognition of EEG. In: IEEE Proceedings on EMBS, pp. 599–602 (2003)Google Scholar