Abstract
The brain-computer interface technology interprets the EEG signals displayed by the human brain’s neurological thinking activities through computers and instruments, and directly uses the interpreted information to manipulate the outside world, thereby abandoning the human peripheral nerves and muscle systems. The emergence of brain-computer interface technology has brought practical value to many fields. Based on the mechanism and characteristics of motion imaging EEG signals, this paper designs the acquisition experiment of EEG signals. After removing the anomalous samples, the wavelet-reconstruction method is used to extract the specific frequency band of the motion imaging EEG signal. According to the characteristics of motor imagery EEG signals, the feature recognition algorithm of convolutional neural networks is discussed. After an in-depth analysis of the reasons for choosing this algorithm, a variety of different network structures were designed and trained. The optimal network structure is selected by analyzing the experimental results, and the reasons why the structure effect is superior to other structures are analyzed. The results show that the method has a high accuracy rate for the recognition of motor imagery EEG, and it has good robustness.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00779-019-01250-z/MediaObjects/779_2019_1250_Fig13_HTML.png)
Similar content being viewed by others
References
Ullah I, Hussain M, Qazi EUH (2018) An automated system for epilepsy detection using EEG brain signals based on deep learning approach. Expert Syst Appl 107(2):61–71
Xiaokang S, Shugeng C, Lin Y (2018) Fast recognition of BCI-inefficient users using physiological features from EEG signals: a screening study of stroke patients. Front Neurosci 12(2):93–96
Kim C, Sun J, Liu D (2018) An effective feature extraction method by power spectral density of EEG signal for 2-class motor imagery-based BCI. Med Biol Eng Comput 55(12):39–46
Wang J, Feng Z, Lu N (2018) Toward optimal feature and time segment selection by divergence method for EEG signals classification. Comput Biol Med 97(8):161–170
Zhaohong D, Peng X, Lixiao X (2018) Transductive joint-knowledge-transfer TSK FS for recognition of epileptic EEG signals. IEEE Trans Neural Syst Rehabil Eng 25(2):1–6
Min W, Sherif A, Nour M (2018) Deep Gaussian mixture-hidden Markov model for classification of EEG signals. IEEE Trans Emerg Topics Comput Intell 2(4):278–287
Jafarifarmand A, Badamchizadeh MA, Khanmohammadi S (2018) A new self-regulated neuro-fuzzy framework for classification of EEG signals in motor imagery BCI. IEEE Trans Fuzzy Syst 26(3):1485–1497
Anil H, Arup S, Rupam B (2018) A discriminant feature level fusion based learning for automatic staging of EEG signals. Healthc Technol Lett 15(4):29–34
Kumar S, Sharma A (2018) A new parameter tuning approach for enhanced motor imagery EEG signal classification. Med Biol Eng Comput 56(10):1861–1874
Yin Z, Zhang J (2018) Task-generic mental fatigue recognition based on neurophysiological signals and dynamical deep extreme learning machine. Neurocomputing 283(12):266–281
Taran S, Bajaj V (2018) Motor imagery tasks-based EEG signals classification using tunable-Q wavelet transform. Neural Comput & Applic 6(2):227–246
Bartosz B, Dariusz M, Cyran KA (2018) A Machine learning approach to the detection of Pilot’s reaction to unexpected events based on EEG signals. Comput Intell Neurosci 35(2):1–9
Mahmoudi M, Shamsi M (2018) Multi-class EEG classification of motor imagery signal by finding optimal time segments and features using SNR-based mutual information. Australas Phys Eng Sci Med 17(9):33–36
Rocha Pinheiro O, Lynn RGA, Josemar RDS (2018) EEG signals classification: motor imagery for driving an intelligent wheelchair. IEEE Lat Am Trans 16(1):254–259
Bairagi, Vinayak (2018) EEG signal analysis for early diagnosis of Alzheimer disease using spectral and wavelet based features. Int J Inf Technol 15(7):239–246
Lixiao X, Zhaohong D, Peng X (2018) Generalized hidden-mapping Transductive transfer learning for recognition of epileptic electroencephalogram signals. IEEE Trans Cybern 35(12):439–446
Chiarelli AM, Croce P, Merla A (2018) Deep learning for hybrid EEG-fNIRS brain-computer Interface: application to motor imagery classification. J Neural Eng 15(3):339–346
Maksimenko VA, Kurkin SA, Pitsik EN (2018) Artificial neural network classification of motor-related EEG: an increase in classification accuracy by reducing signal complexity. Complexity 35:12) :1–12) 10
Yuwei Z, Jiuqi H, Yushu C (2018) Improving generalization based on l1-norm regularization for EEG-based motor imagery classification. Front Neurosci 12(2):272–286
Yilmaz G, Ungan P, Kemal S (2018) EEG-like signals can be synthesized from surface representations of single motor units of facial muscles. Exp Brain Res 236(4):1–11
Funding
The study was supported by the Department of Education of Liaoning Province (Grant No. 2017FWDF03), Natural Science Foundation of Liaoning Province of China (Grant No. 20180550567), University of Science and Technology Liaoning Youth Fund (Grant No. 2017QN05), and Department of Education of Liaoning Province (Grant No. 2016HZZD05).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Shi, T., Ren, L. & Cui, W. Feature recognition of motor imaging EEG signals based on deep learning. Pers Ubiquit Comput 23, 499–510 (2019). https://doi.org/10.1007/s00779-019-01250-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-019-01250-z