Abstract
A motor imagery EEG (MI-EEG) signal is often selected as the driving signal in an active brain computer interface (BCI) system, and it has been a popular field to recognize MI-EEG images via convolutional neural network (CNN), which poses a potential problem for maintaining the integrity of the time-frequency-space information in MI-EEG images and exploring the feature fusion mechanism in the CNN. However, information is excessively compressed in the present MI-EEG image, and the sequential CNN is unfavorable for the comprehensive utilization of local features. In this paper, a multidimensional MI-EEG imaging method is proposed, which is based on time-frequency analysis and the Clough-Tocher (CT) interpolation algorithm. The time-frequency matrix of each electrode is generated via continuous wavelet transform (WT), and the relevant section of frequency is extracted and divided into nine submatrices, the longitudinal sums and lengths of which are calculated along the directions of frequency and time successively to produce a 3 × 3 feature matrix for each electrode. Then, feature matrix of each electrode is interpolated to coincide with their corresponding coordinates, thereby yielding a WT-based multidimensional image, called WTMI. Meanwhile, a multilevel and multiscale feature fusion convolutional neural network (MLMSFFCNN) is designed for WTMI, which has dense information, low signal-to-noise ratio, and strong spatial distribution. Extensive experiments are conducted on the BCI Competition IV 2a and 2b datasets, and accuracies of 92.95% and 97.03% are yielded based on 10-fold cross-validation, respectively, which exceed those of the state-of-the-art imaging methods. The kappa values and p values demonstrate that our method has lower class skew and error costs. The experimental results demonstrate that WTMI can fully represent the time-frequency-space features of MI-EEG and that MLMSFFCNN is beneficial for improving the collection of multiscale features and the fusion recognition of general and abstract features for WTMI.
Graphical abstract
Similar content being viewed by others
References
Qiao W, Bi X (2020) Ternary-task convolutional bidirectional neural turing machine for assessment of EEG-based cognitive workload[J]. Biomedl Signal Process Control 57:101745
Usman SM, Khalid S, Akhtar R, Bortolotto Z, Bashir Z, Qiu H (2019) Using scalp EEG and intracranial EEG signals for predicting epileptic seizures: review of available methodologies[J]. Seizure 71:258–269
Sandheep P, Vineeth S, Poulose M, Subha DP (2019) “Performance analysis of deep learning CNN in classification of depression EEG signals,” TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Kochi, India, 2019: 1339–1344.
Lotte F, Bougrain L, Cichocki A, Clerc M, Congedo M, Rakotomamonjy A, Yger F (2018) A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update[J]. J Neural Eng 15(3):031005
Pfurtscheller G, Neuper C (2001) Motor imagery and direct brain-computer communication[J]. Proc IEEE 89(7):1123–1134
Royer AS, Doud AJ, Rose ML, He B (2010) EEG control of a virtual helicopter in 3-dimensional space using intelligent control strategies[J]. IEEE Trans Neural Syst Rehabil Eng 18(6):581–589
Cahn BR, Polich (2016) Meditation states and traits: EEG, ERP, and neuroimaging studies[J]. Psychol Bull 132(2):180–211
Gouy-Pailler C, Congedo M, Brunner C, Jutten C, Pfurtscheller G (2010) Nonstationary brain source separation for multiclass motor imagery[J]. IEEE Trans Biomed Eng 57(2):469–478
Brunner C, Naeem M, Leeb R, Graimann B, Pfurtscheller G (2007) Spatial filtering and selection of optimized components in four class motor imagery EEG data using independent components analysis[J]. Pattern Recogn Lett 28(8):957–964
Vidaurre C, Kawanabe M, von Bünau P, Blankertz B, Müller KR (2011) Toward unsupervised adaptation of LDA for brain–computer interfaces[J]. IEEE Trans Biomed Eng 58(3):587–597
Dong E, Li C, Li L, du S, Belkacem AN, Chen C (2017) Classification of multi-class motor imagery with a novel hierarchical SVM algorithm for brain–computer interfaces[J]. Med Biol Eng Comput 55(10):1809–1818
Sitaram R, Zhang H, Guan C, Thulasidas M, Hoshi Y, Ishikawa A, Shimizu K, Birbaumer N (2007) Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a brain–computer interface[J]. NeuroImage 34(4):1416–1427
Hu J, Xiao D, Mu Z (2009) Application of energy entropy in motor imagery EEG classification[J]. International Journal of Digital Content Technology and its Applications 3(2):83–90
Alom MZ, Taha TM, Yakopcic C et al (2018) The history began from alexnet: a comprehensive survey on deep learning approaches[J]. arXiv preprint arXiv 1803:01164
Dose H, Møller JS, Iversen HK, Puthusserypady S (2018) An end-to-end deep learning approach to MI-EEG signal classification for BCIs[J]. Expert Syst Appl 114:532–542
Tang Xuebin, Zhao Jinchuang, Fu Wenlin et al (2019) A novel classification algorithm for MI-EEG based on deep learning[C]. 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC):606–611
Wei CS, Koike-Akino T, Wang Y (2019) Spatial component-wise convolutional network (SCCNet) for motor-imagery EEG classification[C]. 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER) 2019:328–331
Yang H, Sakhavi S, Ang KK et al (2015) On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification[C]. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2015:2620–2623
Korhan N, Dokur Z, Olmez T (2019) Motor imagery based EEG classification by using common spatial patterns and convolutional neural networks[C]. 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) 2019:1–4
Sakhavi S, Guan C, Yan S (2015) Parallel convolutional-linear neural network for motor imagery classification[C]. 2015 23rd European Signal Processing Conference (EUSIPCO) 2015:2736–2740
Sakhavi S, Guan C, Yan S (2018) Learning temporal information for brain-computer interface using convolutional neural networks[J]. IEEE Trans Neural Netw Learn Syst 29(11):5619–5629
Zhu X, Li P, Li C et al (2018) Separated channel convolutional neural network to realize the training free motor imagery BCI systems[J]. Biomedl Signal Process Control 49:396–403
Uktveris T, Jusas V (2017) Application of convolutional neural networks to four-class motor imagery classification problem[J]. Journal of Information Technology and Control 46(2):260–273 May
Tabar YR, Halici U (2017) A novel deep learning approach for classification of EEG motor imagery signals[J]. J Neural Eng 14(1):016003
Dai M, Zheng D, Na R, Wang S, Zhang S (2019) EEG classification of motor imagery using a novel deep learning framework[J]. Sensors 19(3):551
Tian G, Liu Y (2018) Study on classification of left-right hands motor imagery EEG signals based on CNN[C]. 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC) 2018:324–329
Wang Zijian, Cao Lei, Zhang Zuo, Gong Xiaoliang, Sun Yaoru, Wang Haoran (2018) Short time Fourier transformation and deep neural networks for motor imagery brain computer interface recognition[J]. Concurrency and Computation: Practice and Experience 30(23):e4413
Tayeb Z, Fedjaev J, Ghaboosi N et al (2019) Validating deep neural networks for online decoding of motor imagery movements from EEG signals[J]. Sensors 19(1):210
Alazrai R, Abuhijleh M, Alwanni H, Daoud MI (2019) A deep learning framework for decoding motor imagery tasks of the same hand using EEG signals[J]. IEEE Access 7:109612–109627
Xu B, Zhang L, Song A et al (2018) Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification[J]. IEEE Access 7:6084–6093
Yu Z, Zhang X et al (2017) Portable brain-computer interface based on novel convolutional neural network[J]. Comput Biol Med 107:248–256
Alfeld P (1984) A trivariate clough—tocher scheme for tetrahedral data[J]. Comput Aided Geom Des 1(2):169–181
Chaudhary S, Taran S, Bajaj V (2019) Convolutional neural network based approach towards motor imagery tasks EEG signals classification[J]. IEEE Sensors J 19(12):4494–4500
Simonyan Karen, Zisserman Andrew(2014) “Very deep convolutional networks for large-scale image recognition,” CoRR, vol. abs/ 1409.1556
Deng Jia, Dong Wei, Socher Richard, Li Li-Jia, Li Kai, Fei-Fei Li (2009) “ImageNet: a large-scale hierarchical image database”, Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops
Xu G, Shen X, Chen S, Zong Y, Zhang C, Yue H, Liu M, Chen F, Che W (2019) A deep transfer convolutional neural network framework for EEG signal classification[J]. IEEE Access 7:112767–112776
Ling SH, Makgawinata H, Monsivais FH et al (2019) Classification of EEG motor imagery tasks using convolution neural networks[C]. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2019:758–761
Zhao Wei, Ye Jianbo, Yang Min, et al. (2018) Investigating capsule networks with dynamic routing for text classification[J]. arXiv preprint arXiv:1804.00538
Ha KW, Jeong JW (2019) Motor imagery EEG classification using capsule networks[J]. Sensors 19(13):2854
Li M-A, Han J-F, Duan L-J (2019) A novel MI-EEG imaging with the location information of electrodes[J]. IEEE Access 8:3197–3211
Amin SU, Alsulaiman M, Muhammad G, Bencherif MA, Hossain MS (2019) Multilevel weighted feature fusion using convolutional neural networks for EEG motor imagery classification[J]. IEEE Access 7:18940–18950
Amin SU, Alsulaiman M, Muhammad G, Mekhtiche MA, Shamim Hossain M (2019) Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion[J]. Futur Gener Comput Syst 101:542–554
Zhao X, Zhang H, Zhu G, You F, Kuang S, Sun L (2019) A multi-branch 3D convolutional neural network for EEG-based motor imagery classification[J]. IEEE Trans Neural Syst Rehabil Eng 27(10):2164–2177
Leeb R, Lee F, Keinrath C, Scherer R, Bischof H, Pfurtscheller G (2007) Brain–computer communication: motivation, aim, and impact of exploring a virtual apartment. IEEE Trans Neural Syst Rehabil Eng 15(4):473–482
Li CH, Lee CK (1993) Minimum cross entropy thresholding[J]. Pattern Recogn 26(4):617–625
Lee GR, Gommers R, Wasilewski F, Wohlfahrt K, O’Leary A (2019) PyWavelets: a Python package for wavelet analysis. J Open Source Softw 4(36):1237
Acknowledgement
We would like to thank the provider of dataset and all of the people who have given us helpful suggestions and advice. The authors are obliged to the anonymous referee for carefully looking over the details and for useful comments that improved this paper.
Funding
The National Natural Science Foundation of China (No. 11832003, No. 61672070) and the Natural Science Foundation of Beijing (No. 7132021, No. 4182009) financially supported this work.
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
Li, Ma., Han, Jf. & Yang, Jf. Automatic feature extraction and fusion recognition of motor imagery EEG using multilevel multiscale CNN . Med Biol Eng Comput 59, 2037–2050 (2021). https://doi.org/10.1007/s11517-021-02396-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-021-02396-w