EEG classification based on channel selection and multi-dimensional feature fusion

doi:10.11772/j.issn.1001-9081.2022101590

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (11): 3418-3427.DOI: 10.11772/j.issn.1001-9081.2022101590

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

EEG classification based on channel selection and multi-dimensional feature fusion

Shuying YANG(), Haiming GUO, Xin LI

School of Computer Science and Engineering，Tianjin University of Technology，Tianjin 300384，China

Received:2022-10-24 Revised:2023-01-31 Accepted:2023-01-31 Online:2023-04-12 Published:2023-11-10
Contact: Shuying YANG
About author:YANG Shuying， born in 1964， Ph. D.， professor. Her research interests include pattern recognition， intelligent robots.
GUO Haiming， born in 1998， M. S. candidate. His research interest includes pattern recognition.
LI Xin， born in 1998， M. S. candidate. His research interest includes pattern recognition.
Supported by:
2019 Key Cultivation Project of Teaching Achievement Award of Tianjin Institute of Educational Science Planning(PYGJ-015);School Level Teaching Fund of Tianjin University of Technology(ZD20-04)

基于通道选择和多维特征融合的脑电信号分类

杨淑莹(), 国海铭, 李欣

天津理工大学计算机科学与工程学院，天津 300384

通讯作者: 杨淑莹
作者简介:杨淑莹（1964—），女，四川成都人，教授，博士，主要研究方向：模式识别、智能机器人 yangshuying@email.tjut.edu.cn
国海铭（1998—），男，河北衡水人，硕士研究生，主要研究方向：模式识别
李欣（1998—），男，安徽六安人，硕士研究生，主要研究方向：模式识别。
基金资助:
2019年天津市教育科学规划院教学成果奖重点培育项目(PYGJ?015);2020年天津理工大学校级重点教学基金资助项目(ZD20?04)

Abstract

Abstract:

To solve the problems of the mutual interference of multi-channel ElectroEncephaloGraphy （EEG）， the different classification results caused by individual differences， and the low recognition rate of single domain features， a method of channel selection and feature fusion was proposed. Firstly， the acquired EEG was preprocessed， and the important channels were selected by using Gradient Boosting Decision Tree （GBDT）. Secondly， the Generalized Predictive Control （GPC） model was used to construct the prediction signals of important channels and distinguish the subtle differences among multi-dimensional correlation signals， then the SE-TCNTA （Squeeze and Excitation block-Temporal Convolutional Network-Temporal Attention） model was used to extract temporal features between different frames. Thirdly， the Pearson correlation coefficient was used to calculate the relationship between channels， the frequency domain features of EEG and the control values of prediction signals were extracted as inputs， the spatial graph structure was established， and the Graph Convolutional Network （GCN） was used to extract the features of frequency domain and spatial domain. Finally， the above two features were input to the fully connected layer for feature fusion in order to realize the classification of EEG. Experimental results on public dataset BCICIV_2a show that in the case of channel selection， compared with the first EEG-inception model for ERP detection and DSCNN （Shallow Double-branch Convolutional Neural Network） model that also uses double branch feature extraction， the proposed method has the classification accuracy increased by 1.47% and 1.69% respectively， and has the Kappa value increased by 1.25% and 2.53% respectively. The proposed method can improve the classification accuracy of EEG and reduce the influence of redundant data on feature extraction， so it is more suitable for Brain-Computer Interface （BCI） systems.

Key words: ElectroEncephaloGraphy (EEG), feature fusion, channel selection, Graph Convolution Network (GCN), Temporal Convolutional Network (TCN), Generalized Predictive Control (GPC) model

摘要：

针对多通道脑电信号（EEG）相互干扰、存在个体差异性导致分类结果不同和单域特征识别率低等问题，提出一种通道选择和特征融合的方法。首先，对获取到的EEG进行预处理，使用梯度提升决策树（GBDT）选出重要通道；其次，采用广义预测控制（GPC）模型构建重要通道的预测信号，辨析多维相关信号之间的细微差别，再使用SE?TCNTA（Squeeze and Excitation block-Temporal Convolutional Network-Temporal Attention）模型提取不同帧之间的时序特征；然后，使用皮尔逊相关系数计算通道间的关系，提取EEG的频域特征和预测信号的控制量作为输入，建立空间图结构，并采用图卷积网络（GCN）提取频域、空域的特征；最后，将上述二者特征输入全连接层进行特征融合，实现EEG的分类。在公共数据集BCICIV_2a上的实验结果表明，在进行通道选择的情况下，与首个用于ERP检测的EEG-Inception模型以及同样采用双分支提取特征的DSCNN （Shallow Double-branch Convolutional Neural Network）模型方法相比，所提方法的分类准确率分别提升了1.47%和1.69%，Kappa值分别提升了1.25%和2.53%。所提方法能够提高EGG的分类精度，同时减少冗余数据对特征提取的影响，因此更适用于脑机接口（BCI）系统。

关键词: 脑电信号, 特征融合, 通道选择, 图卷积网络, 时序卷积网络, 广义预测控制模型

CLC Number:

TP301.6

Shuying YANG, Haiming GUO, Xin LI. EEG classification based on channel selection and multi-dimensional feature fusion[J]. Journal of Computer Applications, 2023, 43(11): 3418-3427.

杨淑莹, 国海铭, 李欣. 基于通道选择和多维特征融合的脑电信号分类[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3418-3427.

Figures/Tables 17

References 34

1	DOUIBI K， LE BARS S， LEMONTEY A， et al. Toward EEG-based BCI applications for Industry 4.0： challenges and possible applications［J］. Frontiers in Human Neuroscience， 2021， 15： No.705064. 10.3389/fnhum.2021.705064
2	MINI P P， THOMAS T， GOPIKAKUMARI R， et al. EEG based direct speech BCI system using a fusion of SMRT and MFCC/LPCC features with ANN classifier［J］. Biomedical Signal Processing and Control， 2021， 68： No.102625. 10.1016/j.bspc.2021.102625
3	VIDAURRE C， JORAJURÍA T， RAMOS-MURGUIALDAY A， et al. Improving motor imagery classification during induced motor perturbations［J］. Journal of Neural Engineering， 2021， 18（4）： No.0460b1. 10.1088/1741-2552/ac123f
4	BAVKAR S， IYER B， DEOSARKAR S， et al. Rapid screening of alcoholism： an EEG based optimal channel selection approach［J］. IEEE Access， 2019， 7：99670-99682. 10.1109/access.2019.2927267
5	LV J， LIU M. Common spatial pattern and particle swarm optimization for channel selection in BCI［C］// Proceedings of the 3rd International Conference on Innovative Computing Information and Control. Piscataway： IEEE， 2008： 457-457. 10.1109/icicic.2008.196
6	ANNABY M H， SAID M H， ELDEIB A M， et al. EEG-based motor imagery classification using digraph Fourier transforms and extreme learning machines［J］. Biomedical Signal Processing and Control， 2021， 69： No.102831. 10.1016/j.bspc.2021.102831
7	RAMOSER H， MÜLLER-GERKING J， PFURTSCHELLER G. Optimal spatial filtering of single trial EEG during imagined hand movement［J］. IEEE Transactions on Rehabilitation Engineering， 2000， 8（4）： 441-446. 10.1109/86.895946
8	ZAHID S Z， AQIL M， TUFAIL M， et al. Online classification of multiple motor imagery tasks using filter bank based maximum-a-posteriori common spatial pattern filters［J］. IRBM， 2020， 41（3）：141-150. 10.1016/j.irbm.2019.11.002
9	ANG K K， CHIN Z Y， ZHANG H， et al. Filter Bank Common Spatial Pattern （FBCSP） in brain-computer interface［C］// Proceedings of the 2008 IEEE International Joint Conference on Neural Networks （IEEE World Congress on Computational Intelligence）. Piscataway： IEEE， 2008： 2390-2397. 10.1109/ijcnn.2008.4634130
10	HAN Y， WANG B， LUO J， et al. A classification method for EEG motor imagery signals based on parallel convolutional neural network［J］. Biomedical Signal Processing and Control， 2022， 71（Pt B）： No.103190. 10.1016/j.bspc.2021.103190
11	VENKATA PHANIKRISHNA B， CHINARA S. Automatic classification methods for detecting drowsiness using wavelet packet transform extracted time-domain features from single-channel EEG signal［J］. Journal of Neuroscience Methods， 2021， 347： No.108927. 10.1016/j.jneumeth.2020.108927
12	SUN B， ZHAO X， ZHANG H， et al. EEG motor imagery classification with sparse spectrotemporal decomposition and deep learning［J］. IEEE Transactions on Automation Science and Engineering， 2021， 18（2）： 541-551. 10.1109/tase.2020.3021456
13	XU M， YAO J， NI H. Dual head and dual attention in deep learning for end-to-end EEG motor imagery classification［J］. Applied Sciences， 2021， 11（22）： No.10906. 10.3390/app112210906
14	TORTORA S， GHIDONI S， CHISARI C， et al. Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network［J］. Journal of Neural Engineering， 2020， 17（4）： No.046011. 10.1088/1741-2552/ab9842
15	FENG N， HU F， WANG H， et al. Motor intention decoding from the upper limb by graph convolutional network based on functional connectivity［J］. International Journal of Neural Systems， 2021， 31（12）： No.2150047. 10.1142/s0129065721500477
16	CHANG Q， LI C C， TIAN Q， et al. Classification of first-episode schizophrenia， chronic schizophrenia and healthy control based on brain network of mismatch negativity by graph neural network［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering， 2021， 29：1784-1794. 10.1109/tnsre.2021.3105669
17	LI H， DING M， ZHANG R， et al. Motor imagery EEG classification algorithm based on CNN-LSTM feature fusion network［J］. Biomedical Signal Processing and Control， 2022， 72（Pt A）： No.103342. 10.1016/j.bspc.2021.103342
18	李红利，丁满，张荣华，等. 基于特征融合神经网络的运动想象脑电分类算法［J］. 中国医学物理学杂志， 2022， 39（1）：69-75. 10.3969/j.issn.1005-202X.2022.01.012
	LI H L， DING M， ZHANG R H， et al. Motor imagery EEG classification algorithm based on feature fusion neural network［J］. Chinese Journal of Medical Physics， 2022， 39（1）： 69-75. 10.3969/j.issn.1005-202X.2022.01.012
19	Institute for Knowledge Discovery， Graz University of Technology. BCI Competition IV — data sets 2a［DB/OL］. ［2022-05-13］. .
20	DEVOS L， MEERT W， DAVIS J. Fast gradient boosting decision trees with bit-level data structures［C］// Proceedings of the 2019 Joint European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS 11906. Cham： Springer， 2020： 590-606.
21	MENDOZA-SOTO J L， RODRÍGUEZ CORTÉS H. Generalized predictive control for trajectory tracking of a quadcopter vehicle［C］// Proceedings of the 2017 International Conference on Unmanned Aircraft Systems. Piscataway： IEEE， 2017： 206-212. 10.1109/icuas.2017.7991368
22	ZHANG T， LI C X， LI Z L. Generalized predictive control and delay compensation for high-speed EMU network control system［C］// Proceedings of the 6th International Conference on Computer Science and Network Technology. Piscataway： IEEE， 2017： 511-515. 10.1109/iccsnt.2017.8343751
23	李红利，尹飞超，张荣华，等. 基于通道注意力和稀疏时频分解的运动想象分类［J］. 生物医学工程学杂志， 2022， 39（3）：488-497. 10.7507/1001-5515.202111031
	LI H L， YIN C F， ZHANG R H， et al. Motor imagery electroencephalogram classification based on sparse spatiotemporal decomposition and channel attention［J］. Journal of Biomedical Engineering， 2022， 39（3）： 488-497. 10.7507/1001-5515.202111031
24	ZHOU Y， ZHENG H， HUANG X， et al. Graph neural networks： taxonomy， advances and trends［J］. ACM Transactions on Intelligent Systems and Technology， 2022， 13（1）： No.15. 10.1145/3495161
25	SCARSELLI F， GORI M， TSOI A C， et al. The graph neural network model［J］. IEEE Transactions on Neural Networks， 2009， 20（1）： 61-80. 10.1109/tnn.2008.2005605
26	SHI X， LV F， SENG D， et al. Visualizing and understanding graph convolutional network［J］. Multimedia Tools and Applications， 2021， 80（6）： 8355-8375. 10.1007/s11042-020-09885-4
27	SALIM A， SUMITRA S. Spectral graph convolutional neural networks in the context of regularization theory［J］. IEEE Transactions on Neural Networks and Learning Systems， 2022（Early Access）： 1-12. 10.1109/tnnls.2022.3177742
28	MA W， GONG Y， XUE H， et al. A lightweight and accurate double-branch neural network for four-class motor imagery classification［J］. Biomedical Signal Processing and Control， 2022， 75： No.103582. 10.1016/j.bspc.2022.103582
29	ZHANG C， KIM Y K， ESKANDARIAN A. EEG-inception： an accurate and robust end-to-end neural network for EEG-based motor imagery classification［J］. Journal of Neural Engineering， 2021， 18（4）： No.046014. 10.1088/1741-2552/abed81
30	ZHAO X， ZHANG H， ZHU G， et al. A multi-branch 3D convolutional neural network for EEG-based motor imagery classification［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering， 2019， 27（10）： 2164-2177. 10.1109/tnsre.2019.2938295
31	CHEN J， YU Z， GU Z， et al. Deep temporal-spatial feature learning for motor imagery-based brain-computer interfaces［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering， 2020， 28（11）： 2356-2366. 10.1109/tnsre.2020.3023417
32	RIYAD M， KHALIL M， ADIB A. A novel multi-scale convolutional neural network for motor imagery classification［J］. Biomedical Signal Processing and Control， 2021， 68： No.102747. 10.1016/j.bspc.2021.102747
33	AMIN S U， ALSULAIMAN M， MUHAMMAD G， et al. Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion［J］. Future Generation Computer Systems， 2019， 101：542-554. 10.1016/j.future.2019.06.027
34	LAWHERN V J， SOLON A J， WAYTOWICH N R， et al. EEGNet： a compact convolutional neural network for EEG-based brain-computer interfaces［J］. Journal of Neural Engineering， 2018， 15（5）： No.056013. 10.1088/1741-2552/aace8c

通道数	不同受试者的准确率									平均值
通道数	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
1	80.69	75.38	80.29	75.68	76.49	83.87	82.56	81.42	85.96	80.26
2	83.62	79.84	78.88	72.28	80.26	83.26	84.54	86.35	80.72	81.08
3	88.31	76.24	81.85	74.56	78.54	84.32	83.30	84.26	82.88	81.58
4	85.60	73.20	81.59	80.54	84.48	83.50	81.58	84.32	85.88	82.29
5	88.27	79.59	87.70	85.68	84.39	83.16	89.49	89.56	86.79	86.07
6	85.89	73.59	83.29	86.12	82.99	83.43	84.29	85.51	85.49	83.40
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
22	78.26	71.28	70.94	78.26	72.40	76.34	80.76	79.84	81.46	76.61

通道数	不同受试者的准确率									平均值
通道数	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
1	80.69	75.38	80.29	75.68	76.49	83.87	82.56	81.42	85.96	80.26
2	83.62	79.84	78.88	72.28	80.26	83.26	84.54	86.35	80.72	81.08
3	88.31	76.24	81.85	74.56	78.54	84.32	83.30	84.26	82.88	81.58
4	85.60	73.20	81.59	80.54	84.48	83.50	81.58	84.32	85.88	82.29
5	88.27	79.59	87.70	85.68	84.39	83.16	89.49	89.56	86.79	86.07
6	85.89	73.59	83.29	86.12	82.99	83.43	84.29	85.51	85.49	83.40
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
22	78.26	71.28	70.94	78.26	72.40	76.34	80.76	79.84	81.46	76.61

模型	网络层	神经元数	输出	激活函数
SE-TCNTA	Input		（None， 11， 25）
	SE-Block		（None， 11， 25）	ReLU hard_Sigmoid
	TCN1	12	（None， 11， 12）
	Dropout			Rate=0.8
	TCN2	6	（None， 11， 6）
	Dropout			Rate=0.6
	Permute		（None， 6， 11）
	Dense	11	（None， 6， 11）	Softmax
	Permute		（None， 6， 11）
	Multiply		（None， 11， 6）
	Flatten		（None， 66）
GCN	Input-Data		（None， None， 280）
	Input-Edge		（None， None， 5）
	GraphConv1	16	（None， 5， 16）	ReLU
	GraphConv2	8	（None， 5， 8）	ReLU
	Flatten		（None， 40）
	Dense	32	（None， 64）	ReLU
	Dense	4	（None， 4）	Softmax

模型	网络层	神经元数	输出	激活函数
SE-TCNTA	Input		（None， 11， 25）
	SE-Block		（None， 11， 25）	ReLU hard_Sigmoid
	TCN1	12	（None， 11， 12）
	Dropout			Rate=0.8
	TCN2	6	（None， 11， 6）
	Dropout			Rate=0.6
	Permute		（None， 6， 11）
	Dense	11	（None， 6， 11）	Softmax
	Permute		（None， 6， 11）
	Multiply		（None， 11， 6）
	Flatten		（None， 66）
GCN	Input-Data		（None， None， 280）
	Input-Edge		（None， None， 5）
	GraphConv1	16	（None， 5， 16）	ReLU
	GraphConv2	8	（None， 5， 8）	ReLU
	Flatten		（None， 40）
	Dense	32	（None， 64）	ReLU
	Dense	4	（None， 4）	Softmax

算法	不同受试者的准确率									平均值
算法	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
GPC-SE-TCNTA	85.27	72.29	87.42	80.24	80.39	82.59	88.27	87.69	85.46	83.30
GCN	88.59	78.83	86.28	83.64	83.72	80.89	86.75	86.49	83.19	84.26
特征融合	88.27	79.59	87.70	85.68	84.39	83.16	89.49	89.56	86.79	86.07

EEG classification based on channel selection and multi-dimensional feature fusion

基于通道选择和多维特征融合的脑电信号分类

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 34

Related Articles 15

Recommended Articles

Metrics

方法	不同受试者的准确率									平均值
方法	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
本文方法	88.27	79.59	87.70	85.68	84.39	83.16	89.49	89.56	86.79	86.07
AMSI-EEGNet^［32］	84.03	55.21	89.58	69.79	66.32	61.46	94.10	85.07	80.90	76.27
M3DCNN^［30］	77.38	60.14	82.93	72.29	75.84	68.99	76.04	76.86	84.67	75.02
FBSF-TSCNN^［31］	85.80	60.10	87.80	64.20	48.60	86.90	83.00	81.60	80.20	72.00
EEG-inception^［29］	81.52	78.68	94.09	80.48	79.66	76.98	91.47	91.36	89.17	84.82
MCNN^［33］	90.21	63.40	89.35	71.16	62.82	47.86	90.86	83.72	82.32	75.72
DSCNN^［28］	92.36	72.22	94.79	81.25	78.82	69.79	95.14	89.24	88.19	84.64

[1]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[2]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[3]	Ruihua LIU, Zihe HAO, Yangyang ZOU. Gait recognition algorithm based on multi-layer refined feature fusion [J]. Journal of Computer Applications, 2024, 44(7): 2250-2257.
[4]	Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977.
[5]	Mengyuan HUANG, Kan CHANG, Mingyang LING, Xinjie WEI, Tuanfa QIN. Progressive enhancement algorithm for low-light images based on layer guidance [J]. Journal of Computer Applications, 2024, 44(6): 1911-1919.
[6]	Guijin HAN, Xinyuan ZHANG, Wentao ZHANG, Ya HUANG. Self-supervised image registration algorithm based on multi-feature fusion [J]. Journal of Computer Applications, 2024, 44(5): 1597-1604.
[7]	Hongtian LI, Xinhao SHI, Weiguo PAN, Cheng XU, Bingxin XU, Jiazheng YUAN. Few-shot object detection via fusing multi-scale and attention mechanism [J]. Journal of Computer Applications, 2024, 44(5): 1437-1444.
[8]	Wangjun SHI, Jing WANG, Xiaojun NING, Youfang LIN. Sleep stage classification model by meta transfer learning in few-shot scenarios [J]. Journal of Computer Applications, 2024, 44(5): 1445-1451.
[9]	Xin LI, Qiao MENG, Junyi HUANGFU, Lingchen MENG. YOLOv5 multi-attribute classification based on separable label collaborative learning [J]. Journal of Computer Applications, 2024, 44(5): 1619-1628.
[10]	Xinye LI, Yening HOU, Yinghui KONG, Zhiqi YAN. Few-shot object detection combining feature fusion and enhanced attention [J]. Journal of Computer Applications, 2024, 44(3): 745-751.
[11]	Zongze JIA, Pengfei GAO, Yinglong MA, Xiaofeng LIU, Haixin XIA. Multi-feature fusion attention-based hierarchical classification method for dialogue act [J]. Journal of Computer Applications, 2024, 44(3): 715-721.
[12]	Zhanjun JIANG, Baijing WU, Long MA, Jing LIAN. Faster-RCNN water-floating garbage recognition based on multi-scale feature and polarized self-attention [J]. Journal of Computer Applications, 2024, 44(3): 938-944.
[13]	Ning WU, Yangyang LUO, Huajie XU. Semantic segmentation method for remote sensing images based on multi-scale feature fusion [J]. Journal of Computer Applications, 2024, 44(3): 737-744.
[14]	Yuliang ZHENG, Yunhua CHEN, Weijie BAI, Pinghua CHEN. Vehicle target detection by fusing event data and image frames [J]. Journal of Computer Applications, 2024, 44(3): 931-937.
[15]	Qiaoling HUANG, Bochuan ZHENG, Zicheng DING, Zedong WU. Improved image inpainting network incorporating supervised attention module and cross-stage feature fusion [J]. Journal of Computer Applications, 2024, 44(2): 572-579.

方法	不同受试者的Kappa值									平均值
方法	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
本文方法	0.90	0.66	0.88	0.78	0.81	0.76	0.86	0.85	0.87	0.81
DSCNN^［28］	0.90	0.63	0.93	0.75	0.72	0.60	0.94	0.86	0.84	0.79
M3DCNN^［30］	0.70	0.46	0.79	0.60	0.54	0.65	0.54	0.70	0.71	0.64
FBSF-TSCNN^［31］	0.81	0.47	0.84	0.52	0.32	0.43	0.77	0.76	0.74	0.63
EEG-inception^［29］	0.85	0.54	0.87	0.78	0.77	0.66	0.95	0.83	0.90	0.80
EEGNet ^［34］	0.79	0.34	0.84	0.51	0.54	0.47	0.82	0.73	0.77	0.65
MCNN ^［33］	0.87	0.51	0.86	0.62	0.50	0.30	0.88	0.78	0.76	0.68

方法	不同受试者的Kappa值									平均值
方法	A01	A02	A03	A04	A05	A06	A07	A08	A09	平均值
本文方法	0.90	0.66	0.88	0.78	0.81	0.76	0.86	0.85	0.87	0.81
DSCNN^［28］	0.90	0.63	0.93	0.75	0.72	0.60	0.94	0.86	0.84	0.79
M3DCNN^［30］	0.70	0.46	0.79	0.60	0.54	0.65	0.54	0.70	0.71	0.64
FBSF-TSCNN^［31］	0.81	0.47	0.84	0.52	0.32	0.43	0.77	0.76	0.74	0.63
EEG-inception^［29］	0.85	0.54	0.87	0.78	0.77	0.66	0.95	0.83	0.90	0.80
EEGNet ^［34］	0.79	0.34	0.84	0.51	0.54	0.47	0.82	0.73	0.77	0.65
MCNN ^［33］	0.87	0.51	0.86	0.62	0.50	0.30	0.88	0.78	0.76	0.68