李文平,徐光华,张凯,张四聪,赵丽娇,李辉

• 1:西安交通大学机械工程学院
• 2:西安交通大学机械制造系统工程国家重点实验室
• 3:西安交通大学经济与金融学院

摘要(Abstract)：

针对现有运动想象脑机接口(MI-BCIs)中，基于深度学习的脑电信号解码网络(EEGNet)时域-空域-频域耦合特征学习能力差、模型训练与推理时间长的问题，提出了一种高效运动想象脑电信号浅层卷积解码网络(Faster-EEGNet)。该网络将第1层二维平面串行卷积优化为所有通道同时进行的串行卷积，完成了各通道信号的时域滤波与空间滤波；在中间深度卷积层对空间模式提取信号进行时域卷积特征提取，然后由深度分离卷积再次提取信号的时间-空间耦合特征，并对其进行模式识别。采用公开数据集进行仿真实验验证，结果表明：Faster-EEGNet网络的运动想象识别准确率与信息传输率相较于EEGNet网络有更好的表现，在本实验的小样本训练场景下也能够取得较好的识别效果；相较于EEGNet网络，Faster-EEGNet网络的训练时间减少了44.8%,模型推理时间减少了43.6%以上。实验结果证明所提Faster-EEGNet网络能够提升运动想象脑机接口系统的识别准确性、便捷性及快速响应性能。

关键词(KeyWords)： 脑电信号;脑机接口;运动想象;深度学习;脑电解码算法

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划资助项目（2021ZD0204300）;; 陕西省重点研发计划资助项目（2021GXLH-Z-008）;; 广州市科技计划资助项目（202206060003）

作者(Author): 李文平,徐光华,张凯,张四聪,赵丽娇,李辉

参考文献(References)：

• [1] WOLPAW J R,BIRBAUMER N,HEETDERKS W J,et al.Brain-computer interface technology:a review of the first international meeting [J].IEEE Transactions on Rehabilitation Engineering,2000,8(2):164-173.
• [2] 王维振，曲皓，雷杨浩，等.下肢运动想象脑机接口的研究进展及康复应用 [J].北京生物医学工程，2023,42(2):204-211.WANG Weizhen,QU Hao,LEI Yanghao,et al.Research progress and rehabilitation application of brain-computer interface based on lower-limb motor imagery [J].Beijing Biomedical Engineering,2023,42(2):204-211.
• [3] 张海军，王浩川.多导联EEG信号分类识别研究 [J].计算机工程与应用，2008,44(24):228-230.ZHANG Haijun,WANG Haochuan.Research on classification and recognition of multi-channel EEG signal [J].Computer Engineering and Applications,2008,44(24):228-230.
• [4] KUMAR J S,BHUVANESWARI P.Analysis of electroencephalography (EEG) signals and its categorization-a study [J].Procedia Engineering,2012,38:2525-2536.
• [5] LI Zheng,O’DOHERTY J E,HANSON T L,et al.Unscented Kalman filter for brain-machine interfaces [J].PLOS One,2009,4(7):e6243.
• [6] VAN ERP J,LOTTE F,TANGERMANN M.Brain-computer interfaces:beyond medical applications [J].Computer,2012,45(4):26-34.
• [7] 王迪，陶庆，张小栋，等.采用改进共空间模式算法的四类表情辅助脑电信号识别方法 [J].西安交通大学学报，2022,56(12):136-143.WANG Di,TAO Qing,ZHANG Xiaodong,et al.Recognition of four-class facial expression electroencephalogram data using improved common spatial pattern algorithm [J].Journal of Xi’an Jiaotong University,2022,56(12):136-143.
• [8] MüLLER-GERKING J,PFURTSCHELLER G,FLYVBJERG H.Designing optimal spatial filters for single-trial EEG classification in a movement task [J].Clinical Neurophysiology,1999,110(5):787-798.
• [9] SONG Xiaomu,YOON S C,PERERA V.Adaptive common spatial pattern for single-trial EEG classification in multisubject BCI [C]//2013 6th International IEEE/EMBS Conference on Neural Engineering (NER).Piscataway,NJ,USA:IEEE,2013:411-414.
• [10] ANG Kaikeng,CHIN Z Y,ZHANG Haihong,et al.Filter bank common spatial pattern (FBCSP) in brain-computer interface [C]//2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).[S.l.]:IEEE,2008:2390-2397.
• [11] HIGASHI H,TANAKA T.Simultaneous design of FIR filter banks and spatial patterns for EEG signal classification [J].IEEE Transactions on Biomedical Engineering,2013,60(4):1100-1110.
• [12] MIAO Yangyang,JIN Jing,DALY I,et al.Learning common Time-Frequency-Spatial patterns for motor imagery classification [J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2021,29:699-707.
• [13] HOU Yimin,CHEN Tao,LUN Xiangmin,et al.A novel method for classification of multi-class motor imagery tasks based on feature fusion [J].Neuroscience Research,2022,176:40-48.
• [14] VOULODIMOS A,DOULAMIS N,DOULAMIS A,et al.Deep learning for computer vision:a brief review [J].Computational Intelligence and Neuroscience,2018,2018:7068349.
• [15] GAVAT I,MILITARU Diana.Deep learning in acoustic modeling for automatic speech recognition and understanding:an overview [C]//2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD).Piscataway,NJ,USA:IEEE,2015:1-8.
• [16] ANTONIADES A,SPYROU L,TOOK C C,et al.Deep learning for epileptic intracranial EEG data [C]//2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).Piscataway,NJ,USA:IEEE,2016:1-6.
• [17] SCHIRRMEISTER R T,SPRINGENBERG J T,FIEDERER L D J,et al.Deep learning with convolutional neural networks for EEG decoding and visualization [J].Human Brain Mapping,2017,38(11):5391-5420.
• [18] 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):056013.
• [19] LIU Xiaolin,SHI Rongye,HUI Qianxin,et al.TCACNet:temporal and channel attention convolutional network for motor imagery classification of EEG-based BCI [J].Information Processing & Management,2022,59(5):103001.
• [20] 宋耀莲，殷喜喆，杨俊.基于时空特征学习Transformer的运动想象脑电解码方法 [J].南京大学学报(自然科学),2023,59(2):313-321.SONG Yaolian,YIN Xizhe,YANG Jun.Transformer based on temporal-spatial feature learning for motor imagery electroencephalogram signal decoding [J].Journal of Nanjing University(Natural Science),2023,59(2):313-321.
• [21] NIU Xiaochen,WU Xiaoguang,XIE Ping,et al.A time-frequency analysis of event-related desynchronization/synchronization based on Gabor filter [C]//Proceeding of the 11th World Congress on Intelligent Control and Automation.Piscataway,NJ,USA:IEEE,2014:5179-5184.
• [22] PADFIELD N,ZABALZA J,ZHAO Huimin,et al.EEG-based brain-computer interfaces using motor-imagery:techniques and challenges [J].Sensors,2019,19(6):1423.
• [23] WU C W.ProdSumNet:reducing model parameters in deep neural networks via product-of-sums matrix decompositions [EB/OL].(2019-05-23) [2022-10-20].https://arxiv.org/abs/1809.02209.
• [24] FLESHER S N,DOWNEY J E,WEISS J M,et al.A brain-computer interface that evokes tactile sensations improves robotic arm control [J].Science,2021,372(6544):831-836.
• [25] CHOLLET F.Xception:deep learning with depthwise separable convolutions [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway,NJ,USA:IEEE,2017:1800-1807.