**8. Conclusions and future prospects**

In this chapter, two deep-learning models named LSTM and GRNN were applied to be embedded into a BCI system for MI-EEG signal classification to identify two imagery movements such as imagining right-hand and left-hand actions. In the proposed BCI system, the Emotiv EPOC IC with tg.SAHARAbox system and g.SAHARA electrodes are used to capture MI-EEG signals on C3, Cz, and C4. In this chapter, we use the Daubechies wavelet to get feature values on db4 and db2 coefficients. The GRNN can make each recurrent unit to capture variable-length sequences adaptively. Modified from LSTM, the GRNN has gating units that modulate the flow of information inside the unit, but without having a separate memory cell. In the GRNN, the parameters at each level are shared through the whole network. From the experimental results, the GRNN can get better performance than other strategies. Additionally, the GRNN can always obtain better performance than the LSTM in the application to control an electric wheelchair.

[4] Wu S-L, Liu Y-T, Hsieh T-Y, Lin Y-Y, Chen C-Y, Chuang C-H, Lin C-T. Fuzzy integral with particle swarm optimization for a motor-imagery-based brain computer interface. IEEE Transactions on Fuzzy Systems. 2016;**2016**. DOI: 10.1109/TFUZZ.2016.2598362 [5] Lin J-S, Lo C-H. Mental commands recognition on motor imagery-based brain computer Interface. International Journal of Computing, Consumer and Control. 2016;**25**:18-25 [6] Chatterjee R, Bandyopadhyay T. EEG based motor imagery classification using SVM and MLP. In: Proceeding of International Conference on Computational Intelligence and

A Motor-Imagery BCI System Based on Deep Learning Networks and Its Applications

http://dx.doi.org/10.5772/intechopen.75009

27

[7] Xie X, Yu ZL, Lu H, Gu Z, Li Y.Motor imagery classification based on bilinear sub-manifold learning of symmetric positive-definite matrices. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2016;**25**:504-516. DOI: 10.1109/TNSRE.2016.2587939 [8] Chatterjeel R, Bandyopadhyal T, Sanyal DK. Effects of wavelets on quality of features in motor imagery EEG signal classification. In: Proceedings of IEEE WiSPNET 2016

[9] Jois K, Garg R, Singh V, Darji A. Comparative analysis of classification techniques for motor imagery based BCI. IEEE Workshop on Computational Intelligence: Theories,

Applications and Future Directions (WCI); 2015. DOI: 10.1109/WCI.2015.7495507 [10] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural net-

[11] Bengio Y, Courville A, Vincent P. Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013;**35**:1798-1828

[12] Graves A. Supervised Sequence Labelling with Recurrent Neural Networks. Studies in

[13] Graves A, Mohamed A-R, Hinton G. Speech recognition with deep recurrent neural networks. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal

[14] Li N, Chen J, Cao H, Zhang B, Natarajan P. Applications of recurrent neural network language model in offline handwriting recognition and word spotting. In: Proceeding of 14th International Conference on Frontiers in Handwriting Recognition; 2014. pp. 134-139

[15] Moghadam SM, Seyyedsalehi SA. Nonlinear analysis of video images using deep recurrent auto-associative neural networks for facial understanding. In: Proceedings of 3rd International Conference on Pattern Recognition and Image Analysis; 2017. pp. 20-25 [16] Petrosian A, Prokhorov D, Homan R, Dasheiff R, Wunsch DII. Recurrent neural network based prediction of epileptic seizures in intra-and extracranial EEG. Neurocomputing.

[17] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;**9**:

Computational Intelligence. Cham Switzerland: Springer; 2012

Networks; 2016. pp. 84-89

Conference; 2016. pp. 1346-1350

works. Science. 2006;**313**(5786):504-507

Processing; May, 2013

2000;**30**(1):201-218

1735-1780
