Feature Recognition of Steady Somatosensory Evoked Potential Based on Convolutional Neural Network
Xu Guizhi1,2#, Hu Zhongtao1,2, Wang Lei1,2, Qi Zhiguang1,2, Guo Miaomiao1,2*
1(State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China); 2(Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province,School of Electrical Engineering, Hebei University of Technology,Tianjin 300130, China)
摘要脑-机接口研究可为瘫痪病人的康复带来一种新的治疗方法。已有研究表明对手指或者正中神经施加一定频率的体感刺激,会引发相同频率且具有空间特异性的稳态体感诱发电位。为优化基于稳态体感诱发电位的脑-机接口的性能,通过快速傅里叶变换寻找12个健康被试的个人左手特定共振频率,采用事件相关谱扰动进行时频分析,检测其稳态体感诱发电位信号。基于共振频率对实验诱发的脑电信号进行1 Hz带通滤波,获得特定频带的数据,采用卷积神经网络(CNN)学习算法对其进行分类,并与采用共空间模式和支持向量机的特征提取及特征分类的方法(CSP+SVM)进行比较。所有被试的结果显示:基于共振频率滤波方法,采用CNN学习算法获得的离线分类准确率均高于85%,并且CNN学习算法的分类准确率显著性优于CSP+SVM的分类准确率(91.8%±5.9% vs 77.4%±8.5%,P<0.05)。因此,在基于稳态体感诱发电位的脑机接口的特征识别中,CNN学习算法相比传统使用的机器学习分类算法(如共空间模式+支持向量机)能够显著提升分类准确率,提高脑机接口的整体性能。
Abstract：Brain-computer interface (BCI) system provides a new way of rehabilitation for patients with aphasia. Previous studies have shown that applying a certain frequency of somatosensory stimulation to the finger or median nerve triggers a spatially-specific steady-state somatosensory evoked potential (SSSEP) with the same frequency. In order to enhance the overall performance of a steady-state somatosensory evoked potentials based BCI system, this work aimed at finding the person-specific resonance-like frequencies of left-hand of 12 healthy subjects by using fast fourier transform (FFT), and the significant time and frequency range for signal feature were selected by event related spectral perturbation (ERSP) for detecting steady-state somatosensory evoked potential signals. The experimentally induced EEG signals were filtered by 1 Hz band-pass based on person-specific resonance-like frequencies to obtain the data of the specific frequency band, then the convolutional neural network (CNN) learning algorithm is used to classify the data. The methods of feature extraction and classification using common spatial pattern (CSP) and support vector machine (SVM) was ompared. The results of all the subjects showed that the accuracy of offline classification obtained by CNN learning algorithm was higher than 85% based on the person-specific resonance-like frequencies filtering method, and the classification accuracy of CNN learning algorithm was higher than using of CSP with SVM (91.8%±5.9% vs 77.4%±8.5%,P<0.05). Therefore, compared with the traditional machine learning classification algorithm (such as common spatial pattern with support vector machine), the CNN learning algorithm can significantly improveed the classification accuracy for feature recognition of brain-computer interface based on steady-state somatosensory evoked potential, and improved the overall performance of the brain-computer interface
[1] 尧德中, 刘铁军, 雷旭, 等. 基于脑电的脑-机接口:关键技术和应用前景[J]. 电子科技大学学报, 2009, 38(5): 550-554. [2] Obermaier B, Neuper C, Guger C, et al. Information transfer rate in a five-classes brain-computer interface.[J]. IEEE Trans Neural Syst Rehabil Eng, 2001, 9(3):283-288. [3] Pfurtscheller G, Neuper C, Müller GR, et al. Graz-BCI: state of the art and clinical applications[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2003, 11(2):1-4. [4] Guger C, Edlinger G, Harkam W, et al. How many people are able to operate an EEG-based brain-computer interface (BCI)?[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2003, 11(2):145. [5] Pfurtscheller G, Müller GR, Pfurtscheller J, et al. ‘Thought’--control of functional electrical stimulation to restore hand grasp in a patient with tetraplegia[J]. Neuroscience Letters, 2003, 351(1):33-36. [6] Hinterberger T, Neumann N, Pham M, et al. A multimodal brain-based feedback and communication system..[J]. Experimental Brain Research, 2004, 154(4):521-526. [7] Müller-Putz GR, Scherer R, Neuper C, et al. Steady-state somatosensory evoked potentials: suitable brain signals for brain-computer interfaces?[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2006, 14(1):30-37. [8] Wang Yi, Wang Yi, Qiu Shilun, et al. Enhancing performance of a motor imagery based brain-computer interface by incorporating electrical stimulation-induced SSSEP[J]. Journal of Neural Engineering, 2016, 14(2):026002 [9] Breitwieser C, Kaiser V, Neuper C, et al. Stability and distribution of steady-state somatosensory evoked potentials elicited by vibro-tactile stimulation[J]. Medical & Biological Engineering & Computing, 2012, 50(4):347-357. [10] Yao Lin, Meng Jianjun, Zhang Dingguo, et al. Selective sensation based brain-computer interface via mechanical vibrotactile stimulation[J]. PLoS ONE, 2013, 8(6):e64784. [11] Kee YJ, Won DO, Lee SW. Classification of left and right foot movement intention based on steady-state somatosensory evoked potentials[C]// International Winter Conference on Brain-Computer Interface. Seoul: IEEE, 2017:106-108. [12] 奕伟波. 复合运动想象诱发下的脑电响应机制与解码技术研究[D]. 天津:天津大学,2017. [13] Rutkowski TM, Mori H.Tactile and boneconduction auditory brain computer interface for vision and hearing impaired users[J].Journal of Neuroscience Methods, 2015, 244 (4):45-51. [14] Pu Jingbo, An Xingwei, Li Jiewei, et al. A preliminary study of brain-computer interface paradigm based on electrical somatosensory modality[J]. Nanotechnology & Precision Engineering, 2015, 13(5):376-382. [15] 李佳宁, 蒲江波, 崔红岩, 等. 基于体感电刺激诱发P300的脑机接口[J]. 仪器仪表学报, 2017,38(6):130-137. [16] Lawrence S, Giles CL, Tsoi AC, et al. Face recognition:A convolutional neural-network approach[J]. IEEE Transactions on Neural Net-Works, 1997, 8(1): 98-113. [17] Abdel-Hamid O, Mahamed A,Jiang H, et al. Applying convolutional neural networks concepts to hybrid NN-HMM modle for speech recognition//Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal(ICASSP). Kyoto:IEEE, 2012: 4277-4280. [18] Deng Li, Hinton G, Kingsbury B. New types of deep neural network learning for speech recognition and related applications: an overview[C]// IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver: IEEE, 2013:8599-8603. [19] Lawrence S, Giles CL, Tsoi AC, et al. Face recognition: a convolutional neural-network approach [J]. IEEE Transactions on Neural Networks, 1997, 8(1):98-113. [20] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. Nevada: Curran Associates Inc. 2012:1097-1105. [21] 赵志宏, 杨绍普, 马增强. 基于卷积神经网络LeNet-5的车牌字符识别研究[J]. 系统仿真学报, 2010, 22(3):638-641. [22] 唐智川, 张克俊, 李超,等. 基于深度卷积神经网络的运动想象分类及其在脑控外骨骼中的应用[J]. 计算机学报, 2017, 40(6):1367-1378. [23] Cecotti H, Graser A. Convolutional neural networks for P300 detection with application to brain-computer interfaces[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(3):433. [24] Salenius S, Schnitzler A, Salmelin R, et al. Modulation of human cortical rolandic rhythms during natural sensorimotor tasks[J]. Neuroimage, 1997, 5(3):221-228. [25] Chen Renkun, Corwell B, Hallett M. Modulation of motor cortex excitability by median nerve and digit stimulation[J]. Experimental Brain Research, 1999, 129(1):77-86. [26] Dockstader C, Cheyne D, Tannock R. Cortical dynamics of selective attention to somatosensory events[J]. Neuroimage, 2010, 49(2):1777-1785. [27] Wang Li, Zhang Xiong, Zhong Xuefei, et al. Analysis and classification of speech imagery EEG for BCI [J]. Biomedical Signal Processing & Control, 2013, 8(6):901-908. [28] Wang Jing, Xu Weiwei. Research of video advertisements effect based on EEG: ERSP and emotion for commercial effect [C]//International Conference on Service Systems and Service Management. Kunming: IEEE, 2016: 1-5. [29] Lahiri R, Rakshit A, Konar A. Discriminating Motor Imagery EEG signals using an improvised regularised CSP algorithm [C]//IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems. New Delhi: IEEE, 2017,35(3): 1-6 [30] Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement[J]. IEEE Transactions on Rehabilitation Engineering A Publication of the IEEE Engineering in Medicine & Biology Society, 2000, 8(4):441-446.. [31] Foss S, Korshunov D, Zachary S. Convolutions of long-tailed and subexponential distributions [J]. Journal of Applied Probability, 2009; 46(3):756-767. [32] Szegedy C, Liu Wei, Jia Yangqing, et al. Going deeper with convolutions[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015:1-9. [33] 孔祥浩, 马琳, 薄洪健,等. CNN与CSP相结合的脑电特征提取与识别方法研究[J]. 信号处理, 34(2):164-173.
