EEG_GENet: A feature-level graph embedding method for motor imagery classification based on EEG signals

• Autorzy: Wang Huiyang , Yu Hua , Wang Haixian

Identyfikatory

DOI

10.1016/j.bbe.2022.08.003

• Języki publikacji: EN

Abstrakty

EN

In recent years, the success of deep learning has driven the development of motor imagery brain-computer interfaces (MI-BCIs) based on electroencephalography (EEG). However, unlike image or language data, motor imagery EEG signals are of multielectrodes with topology information. As a means of integrating graph topology information into feature maps, few studies studied motor imagery classification involving graph embeddings. To decode EEG signals more accurately, this paper proposes a feature-level graph embedding method and combines the method with EEGNet; this new network is called EEG_GENet. Specifically, time-domain features are obtained by convoluting raw EEG signals for each electrode. Then, the adjacent matrix, conceptualized as a graph filter, performs graph convolution and uses the time-domain features to embed the topology information. This process can also perform multi-order graph embeddings. In addition, the adjacency matrix in this paper can adapt to different brain network connectivities for different subjects. We evaluate the proposed method on two benchmark EEG datasets for motor imagery classification. Experimental results on the BCICIV-2a and High_Gamma datasets demonstrate that EEG_GENet achieves 79.57% and 96.02% classification accuracy, respectively. These results indicate that the proposed method is superior to state-of-the-art methods. In addition, various ablation experiments further verify the advantages of the feature-level graph embedding method. To conclude, the feature-level graph embedding method can improves the network’s ability to decode raw motor imagery EEG signals.

Słowa kluczowe

EN

BCIs; brain computer interface; EEG; electroencephalography; motor imagery; deep learning; graph embedding

PL

BCIs; interfejs mózg-komputer; EEG; elektroencefalografia; uczenie głębokie

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 3
• Strony: 1023--1040
• Opis fizyczny: Bibliogr. 56 poz., rys., tab., wykr.

Twórcy

autor

Wang Huiyang

• Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, PR China
• Institute of Artificial Intelligence of Hefei Comprehensive National Science Center, Hefei, Anhui, PR China

autor

Yu Hua

• Department of Cardiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, PR China

autor

Wang Haixian

• Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing 210096, Jiangsu, PR China
• Institute of Artificial Intelligence of Hefei Comprehensive National Science Center, Hefei, Anhui, PR China

Bibliografia

• [1] Cantillo-Negrete J, Carino-Escobar RI, Carrillo-Mora P, Barraza-Madrigal JA, Arias-Carrión O. Robotic orthosis compared to virtual hand for brain-computer interface feedback. Biocybern Biomed Eng 2019;39(2):263–72.
• [2] Zapała D, Zabielska-Mendyk E, Augustynowicz P, Cudo A, Jaśkiewicz M, Szewczyk M, et al. The effects of handedness on sensorimotor rhythm desynchronization and moto-rimagery BCI control. Sci Reports 2020;10(1):1–1.
• [3] Tong J, Zhu D. Multi-phase cycle coding for SSVEP based brain-computer interfaces. Biomed Eng Online 2015;14(1):1–3.
• [4] Ajami S, MahnamA, Abootalebi V. Development of a practical high frequency brain-computer interface based on steady-state visual evoked potentials using a single channel of EEG. Biocybern Biomed Eng 2018;38(1):106–14.
• [5] Meng J, Streitz T, Gulachek N, Suma D, He B. Three-dimensional brain-computer interface control through simultaneous overt spatial attentional and motor imagery tasks. IEEE Trans Biomed Eng 2018;65(11):2417–27.
• [6] Santamaria L, James C. Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems. Healthcare Technol Lett 2018;5(3):88–93.
• [7] Yu Y, Zhou Z, Liu Y, Jiang J, Yin E, Zhang N, et al. Self-paced operation of a wheelchair based on a hybrid brain-computer interface combining motor imagery and P300 potential. IEEE Trans Neural Syst Rehabil Eng 2017;25(12):2516–26.
• [8] Frolov AA, Mokienko O, Lyukmanov R, Biryukova E, Kotov S, Turbina L, et al. Post-stroke rehabilitation training with a motor-imagery-based brain-computer interface (BCI)-controlled hand exoskeleton: A randomized controlled multicenter trial. Front Neurosci 2017;11:400.
• [9] Chinbat O, Lin JS. Prosthetic arm control by human brain. In: 2018 IEEE International Symposium on Computer, Consumer and Control (IS3C). p. 54-57.
• [10] Xu B, Li W, He X, Wei Z, Zhang D, Wu C, et al. Motor imagery based continuous teleoperation robot control with tactile feedback. Electronics 2020;9(1):174.
• [11] Xu F, Miao Y, Sun Y, Guo D, Xu J, Wang Y, et al. A transfer learning framework based on motor imagery rehabilitation for stroke. Sci Rep 2021;11(1):1–9.
• [12] Lu RR, Zheng MX, Li J, Gao TH, Hua XY, Liu G, et al. Motor imagery based brain-computer interface control of continuous passive motion for wrist extension recovery in chronic stroke patients. Neurosci Lett 2020;718 134727.
• [13] Cuomo G, Maglianella V, Ghanbari Ghooshchy S, Zoccolotti P, Martelli M, Paolucci S, et al. Motor imagery and gait control in Parkinson’s disease: techniques and new perspectives in neurorehabilitation. Expert Rev Neurotherap 2022 (justaccepted).
• [14] Zeng H, Song A, Yan R, Qin H. EOG artifact correction from EEG recording using stationary subspace analysis and empirical mode decomposition. Sensors 2013;13(11):14839–59.
• [15] Sharma M, Goyal D, Achuth PV, Acharya UR. An accurate sleep stages classification system using a new class of optimally time-frequency localized three-band wavelet filter bank. Comput Biol Med 2018;98:58–75.
• [16] Alzahab NA, Alimam H, Alnahhas MS, Alarja A, Marmar Z. Determining the optimal feature for two classes motor-imagery brain-computer interface (L/R-MI-BCI) systems in different binary classifiers. Int J Mech Mech Eng 2019;19(1):132–50.
• [17] Hamedi M, Salleh SH, Noor AM. Electroencephalographic motor imagery brain connectivity analysis for BCI: a review. Neural Comput 2016;28(6):999–1041.
• [18] Zhang Y, Liu B, Ji X, Huang D. Classification of EEG signals based on autoregressive model and wavelet packet decomposition. Neural Process Lett 2017;45(2):365–78.
• [19] Aggarwal S, Chugh N. Signal processing techniques for motor imagery brain computer interface: A review. Array 2019;1100003.
• [20] Yang J, Ma Z, Shen T. Multi-time and multi-band CSP motor imagery EEG feature classification algorithm. Appl Sci 2021;11(21):10294.
• [21] Buccino AP, Keles HO, Omurtag A. Hybrid EEG-fNIRS asynchronous brain-computer interface for multiple motor tasks. PLoS ONE 2016;11(1):e0146610.
• [22] Park SH, Lee D, Lee SG. Filter bank regularized common spatial pattern ensemble for small sample motor imagery classification. IEEE Trans Neural Syst Rehabil Eng 2017;26(2):498–505.
• [23] Ghanbar KD, Rezaii TY, Tinati MA, Farzamnia A. Correlation-based regularized common spatial patterns for classification of motor imagery EEG signals. In: 2019 IEEE 27th Iranian Conference on Electrical Engineering (ICEE). p. 1770-1774.
• [24] Blinowska KJ, Lachert P, Kamiński M, Żygierewicz J, Liebert A. Causal coupling of low frequency oscillations during movement imagination-A multimodal study. In: 2021 International Conference on Bioengineering and Biomedical Signal and Image Processing (BIOMESIP). p. 107–111.
• [25] Rozado D, Duenser A, Howell B. Improving the performance of an EEG-based motor imagery brain computer interface using task evoked changes in pupil diameter. PLoS ONE 2015;10(3):e0121262.
• [26] Rodriguez-Ugarte MD, Iáñez E, Ortiz-Garcia M, Azorín JM. Effects of tDCS on real-time BCI detection of pedaling motor imagery. Sensors 2018;18(4):1136.
• [27] Misawa T, Matsuda J, Hirobayashi S. A single-trial nulticlass classification of various motor imagery tasks for EEG-based brain-computer interface communication. Electron Commun Jpn 2017;100(1):18–26.
• [28] Guan S, Zhao K, Yang S. Motor imagery EEG classification based on decision tree framework and Riemannian geometry. Comput Intelligence Neurosci 2019;1:13.
• [29] Oikonomou VP, Georgiadis K, Liaros G, Nikolopoulos S, Kompatsiaris I. A comparison study on EEG signal processing techniques using motor imagery EEG data. In: 2017 IEEE 30th International Symposium on Computer-based Medical Systems (CBMS). p. 781–786.
• [30] Alazrai R, Abuhijleh M, Alwanni H, Daoud MI. A deep learning framework for decoding motor imagery tasks of the same hand using eeg signals. IEEE Access 2019;7:109612–27.
• [31] Ak A, Topuz V, Midi I. Motor imagery EEG signal classification using image processing technique over GoogLeNet deep learning algorithm for controlling the robot manipulator. Biomed Signal Process Control 2022;72 103295.
• [32] Ortiz-Echeverri CJ, Salazar-Colores S, Rodríguez-Reséndiz J, Go´mez-Loenzo RA. A new approach for motor imagery classification based on sorted blind source separation, continuous wavelet transform, and convolutional neural network. Sensors 2019;19(20):4541.
• [33] Chaudhary S, Taran S, Bajaj V, Sengur A. Convolutional neural network based approach towards motor imagery tasks EEG signals classification. IEEE Sens J 2019;19(12):4494–500.
• [34] Schirrmeister RT, Springenberg JT, Fiederer LD, Glasstetter M, Eggensperger K, Tangermann M, et al. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp 2017;38(11):5391–420.
• [35] Ang KK, Chin ZY, Zhang H, Guan C. Filter bank common spatial pattern (FBCSP) in brain-computer interface. In: 2008 IEEE International Joint Conference on Neural Networks (CNN).p. 2390–2397.
• [36] Lawhern VJ, Solon AJ, Waytowich NR, Gordon SM, Hung CP, Lance BJ. EEGNet: A compact convolutional neural network for EEG-based brain-computer interfaces. J Neural Eng 2018;15(5) 056013.
• [37] Tang X, Zhang X. Conditional adversarial domain adaptation neural network for motor imagery EEG decoding. Entropy 2020;22(1):96.
• [38] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: 2017 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). p. 4700-4708.
• [39] Qiao W, Bi X. Deep spatial-temporal neural network for classification of EEG-based motor imagery. In: 2019 Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science (AICS). p. 265-272.
• [40] Izzuddin TA, Safri NM, Othman MA. Compact convolutional neural network (CNN) based on sincnet for end-to-end motor imagery decoding and analysis. Biocybern Biomed Eng 2021;41(4):1629–45.
• [41] Mattioli F, Porcaro C, Baldassarre G. A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface. J Neural Eng 2022;18(6) 066053.
• [42] Bassett DS, Sporns O. Network neuroscience. Nat Neurosci 2017;20(3):353–64.
• [43] Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. arXiv:1312.6203, Dec.2013.
• [44] Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. Adv Neural Inf Process Syst 2016;29:3844–52.
• [45] Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907, Sep. 2016.
• [46] Nt H, Maehara T. Revisiting graph neural networks: All we have is low-pass filters. arXiv:1905.09550, May. 2019.
• [47] Lun X, Jia S, Hou Y, Shi Y, Li Y, Yang H, et al. GCNs-net: A graph convolutional neural network approach for decoding time-resolved eeg motor imagery signals. arXiv:2006.08924, Jun. 2020.
• [48] Zhang D, Chen K, Jian D, Yao L. Motor imagery classification via temporal attention cues of graph embedded EEG signals. IEEE J Biomed Health Inf 2020;24(9):2570–9.
• [49] Li Y, Zhong N, Taniar D, Zhang H. MutualGraphNet: A novel model for motor imagery classification. arXiv:2109.04361, Sep. 2021.
• [50] Brunner C, Leeb R, Müller-Putz G, Schlögl A, Pfurtscheller G. ‘‘BCI Competition 2008-Graz data set A,” Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces). Graz Univ Technol 2008;16:1–6.
• [51] Wei CS, Koike-Akino T, Wang Y. Spatial component-wise convolutional network (SCCNet) for motor-imagery EEG classification. In: 2019 IEEE 9th International IEEE/EMBS Conference on Neural Engineering (NER). p. 328-331.
• [52] Amin SU, Alsulaiman M, Muhammad G, Mekhtiche MA, Hossain MS. Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Generat Comp Syst 2019;101:542–54.
• [53] Lu P, Gao N, Lu Z, Yang J, Bai O, Li Q. Combined CNN and LSTM for motor imagery classification. In: 2019 IEEE 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). p. 1-6.
• [54] Li H, Ding M, Zhang R, Xiu C. Motor imagery EEG classification algorithm based on CNN-LSTM feature fusion network. Biomed Signal Process Control 2022;72 103342.
• [55] Ingolfsson TM, Hersche M, Wang X, Kobayashi N, Cavigelli L, Benini L. EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery brain-machine interfaces. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). p. 2958–2965.
• [56] Wu H, Niu Y, Li F, Li Y, Fu B, Shi G, et al. A parallel multiscale filter bank convolutional neural networks for motor imagery EEG classification. Front Neurosci 2019;13:1275.