Abstract
Electrocephalogram(EEG) signals classification is an important problem in the field of brain computer interface. There are many EEG signals classification methods, but most of are not very efficient in this problem. Deep learning had been broadly used in image classification and has significant performance in classifying images. This paper proposes a comprehensive spatio-temporal feature classification method based on deep learning. It combines Convolutional Neural Network (CNN) and Long-term Short-term Memory network (LSTM) to the motor imaginary EEG classification. Experimental results show that it can preserve spatial, frequency and temporal features of motor imaginary EEG simultaneously and improves the classification accuracy of EEG signals.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, L.: Based on the motion imaging of brain electrical signal classification and brain-computer interface technology, Hebei University of Technology (2011). (in Chinese)
LI, D.: Research on brain-computer interface algorithm based on motion imaging, South China University of Technology (2011). (in Chinese)
Wu, X.: Time-frequency analysis and its application in EEG signal analysis, Dalian University of Technology (2005). (in Chinese)
Li, X.: EEG-based EEG extraction based on independent component analysis and common spatial model. Chin. J. Biomed. Eng. 27(06), 1370–1374 (2010)
Yao, D., Liu, T., Lei, X.: Electroencephalogram based brain-computer interface: key techniques and application prospect. J. Univ. Electron. Sci. Technol. China 38(5), 550–554 (2009)
Guo, J., Yang, B., Ma, S.: Identification of common molecular subsequences. Beijing Biomed. Eng. 29(3), 261–265 (2010)
Li, L., Huang, S., Wu, X., Xiong, D.: EEG feature extraction and classification based on motor imaginary. J. Med. Health Care Equip. 32(01), 16–17 (2011)
Liu, C., Zhao, H., Li, C., Wang, H.: Classification of motor imaging EEG signals based on CSP and SVM. J. Northeast. Univ. (Nat. Sci.) 31(8), 1098–1101 (2010)
Cecotti, H., Graser, A.: Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans. Pattern Anal. Mach. Intell. 33(3), 433 (2011)
Cai, B.: Facility and spatial analysis of single ERP in face recognition and its application to rapid retrieval, Zhejiang University (2015). (in Chinese)
Tabar, Y., Halici, U.: A novel deep learning approach for classification of EEG motor imagery signals. J. Neural Eng. 14(1), 016003 (2016)
Walker, I.: Deep convolutional neural networks for brain computer interface using motor imaginary. Thomson Reuters, London (2015)
Tang, Z., Zhang, K., Li, C., Sun, S., Huang, Q., Zhang, S.: Identification of common molecularmotion imaginary classification based on deep convolutional neural network and its application in brain control exoskeleton. Chin. J. Comput. 254, 1–15 (2017)
Pfurtscheller, G., Aranibar, A.: Event-related cortical desynchronization detected by power measurements of scalp EEG. Electroencephalogram Clin. Neurophysiol. 42(6), 817–826 (1977)
Kuo, C.: Understanding convolutional neural networks with a mathematical model. J. Vis. Commun. Image Represent. 41, 406–413 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, H., Mo, W. (2018). Motor Imaginary EEG Signals Classification Based on Deep Learning. In: Qiao, J., et al. Bio-inspired Computing: Theories and Applications. BIC-TA 2018. Communications in Computer and Information Science, vol 951. Springer, Singapore. https://doi.org/10.1007/978-981-13-2826-8_13
Download citation
DOI: https://doi.org/10.1007/978-981-13-2826-8_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2825-1
Online ISBN: 978-981-13-2826-8
eBook Packages: Computer ScienceComputer Science (R0)