基于改进共空间模式与视觉反馈的闭环脑机接口

doi:10.3901/JME.2019.11.028

机械工程学报 ›› 2019, Vol. 55 ›› Issue (11): 28-35.doi: 10.3901/JME.2019.11.028

• 特邀专栏：共融机器人 • 上一篇下一篇

基于改进共空间模式与视觉反馈的闭环脑机接口

任士鑫^1,2, 王卫群^1,2, 侯增广^1,2, 陈霸东³, 石伟国^1,2, 王佳星^1,2, 梁旭^1,2

1. 中国科学院自动化研究所北京 100190;
2. 中国科学院大学北京 100049;
3. 西安交通大学人工智能与机器人研究所西安 710049

收稿日期:2018-10-15 修回日期:2019-01-24 出版日期:2019-06-05 发布日期:2019-06-05
通讯作者: 王卫群(通信作者),男,1979年出生,博士,副研究员,硕士研究生导师。主要研究方向为康复机器人,人机交互控制,生理电信号处理。E-mail:weiqun.wang@ia.ac.cn
作者简介:任士鑫,男,1993年出生,博士研究生。主要研究方向为康复机器人交互控制,脑机接口。E-mail:renshixin2015@ia.ac.cn;侯增广,男,1969年出生,博士,研究员,博士研究生导师。主要研究方向为机器人与智能系统,康复机器人与微创介入手术机器人。E-mail:zengguang.hou@ia.ac.cn;陈霸东,男,1974年出生,博士,教授,博士研究生导师。主要研究方向为信息论学习,信号处理及脑机接口。E-mail:chenbd@mail.xjtu.edu.cn;石伟国,男,1994年出生,硕士研究生。主要研究方向为康复机器人。E-mail:shiweiguo2017@ia.ac.cn;王佳星,女,1992年出生,博士研究生。主要研究方向为康复机器人。E-mail:wangjiaxing2016@ia.ac.cn;梁旭,男,1991年出生,博士研究生。主要研究方向为康复机器人。E-mail:liangxu2013@ia.ac.cn
基金资助:
国家自然科学基金（91648208，91848110）、北京市自然科学基金（3171001，L172050）和中国科学院战略性先导科技专项（B类，XDB32000000）资助项目。

Closed Loop Brain Computer Interface Based on Improved Common Spatial Patterns and Visual Feedback

REN Shixin^1,2, WANG Weiqun^1,2, HOU Zengguang^1,2, CHEN Badong³, SHI Weiguo^1,2, WANG Jiaxing^1,2, LIANG Xu^1,2

1. Institute of Automation Chinese Academy of Sciences, Beijing 100190;
2. University of Chinese Academy of Sciences, Beijing 100049;
3. Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University, Xi'an 710049

Received:2018-10-15 Revised:2019-01-24 Online:2019-06-05 Published:2019-06-05

摘要/Abstract

摘要： 为提高脑卒中等神经损伤患者在下肢康复训练过程中的主动参与度，设计了基于人体下肢运动想象与视觉反馈的在线闭环脑机接口，并建立了基于互相关熵诱导度量与子频带分析的改进共空间模式算法，提高人体下肢运动意图的识别率。针对运动想象脑电信号信噪比低和难以精确识别等问题，在传统共空间模式算法基础上，利用互相关熵诱导度量准则改进其目标函数，实现了目标函数中距离项属性的动态调整，降低对噪声的敏感性，提高算法鲁棒性；利用脑电信号不同频段蕴含信息不同的特点，使用9个子频带滤波器对信号进行滤波，对每个子频带信号分别提取特征，并进行特征融合，建立基于互相关熵诱导度量与子频带分析的改进共空间模式算法。其次，基于人体下肢运动想象的脑控试验范式，收集下肢运动想象（空想、脚动和腿动）的脑电数据，采用支持向量机（SVM）建立分类模型，优化设计模型参数。在上述研究基础上，建立了以改进共空间模式为特征提取算法，SVM为分类器的脑机接口。进而，在被试执行运动想象的同时，通过虚拟现实场景中虚拟人物的肢体动作给予用户视觉反馈，构建了闭环的脑机交互系统。通过试验验证了改进共空间模式算法的有效性和闭环脑机接口的可行性，初步实现了闭环脑机交互接口。

关键词: 共空间模式, 互相关熵诱导度量, 脑机接口, 运动想象

Abstract: In order to improve the active participation of patients with stroke or nerve injury in the lower limb rehabilitation training, an on-line closed loop brain computer interface is designed based on human lower limb motor imagery and visual feedback. And an improved common spatial pattern algorithm, which based on the correntropy induced metric and sub-frequency band analysis, is established to improve the recognition rate of the motor intention. Due to the low signal noise ratio and classification accuracy of the motor imagery EEG signals, correntropy induced metric is adopted to improve the objective function of the traditional common spatial patterns (CSP). The distance term of the objective function can be adjusted dynamically to alleviate the negative effects of noise. Because the different frequency band signals have different information, nine sub-frequency bandpass filters are used to filter the signal. And the features extracted from each sub-band signal are fused. Therefore, the improved common spatial pattern algorithm based on the correntropy induced metric and sub-frequency band analysis is established. Then, based on the brain control experiment paradigm of human lower limb motor imagery, EEG data of lower limbs motor imagery (idle, foot and leg) are collected. Support vector machine (SVM) is optimized as a classification model for the motor imagery. Based on the study above, a brain computer interface based on improved common spatial pattern algorithm and SVM is built. When participant images the movements, the user's visual feedback is given to the user through the body movements of the virtual character in the virtual reality scene, and a closed loop brain computer interaction system is constructed. Experiments verified the effectiveness of the improved common space algorithm and the feasibility of closed-loop brain computer interface, and the closed loop interaction between the brain and computer is achieved initially.

Key words: brain-computer interface, common spatial patterns, correntropy induced metric, motor imagery

中图分类号:

TG156

任士鑫, 王卫群, 侯增广, 陈霸东, 石伟国, 王佳星, 梁旭. 基于改进共空间模式与视觉反馈的闭环脑机接口[J]. 机械工程学报, 2019, 55(11): 28-35.

REN Shixin, WANG Weiqun, HOU Zengguang, CHEN Badong, SHI Weiguo, WANG Jiaxing, LIANG Xu. Closed Loop Brain Computer Interface Based on Improved Common Spatial Patterns and Visual Feedback[J]. Journal of Mechanical Engineering, 2019, 55(11): 28-35.

参考文献

[1] WOLPAW J R,TENNISSEN A M. Activity-dependent spinal cord plasticity in health and disease[J]. Annual Review of Neuroscience,2001,24(1):807-843.
[2] 侯增广,赵新刚,程龙,等. 康复机器人与智能辅助系统的研究进展[J]. 自动化学报,2016,42(12):1765-1779. HOU Zengguang,ZHAO Xingang,CHENG Long,et al. Recent advances in rehabilitation robots and intelligent assistance systems[J]. Acta Automatica Sinica,2016,42(12):1765-1779.
[3] WANG Congzhe,FANG Yuefa,GUO Sheng. Multi-objective optimization of a parallel ankle rehabilitation robot using modified differential evolution algorithm[J]. Chinese Journal of Mechanical Engineering,2015,28(4):702-715.
[4] 倪自强,王田苗,刘达. 医疗机器人技术发展综述[J]. 机械工程学报,2015,51(13):45-52. Ni Ziqiang,WANG Tianmiao,LIU Da. Survey on medical robotics[J]. Journal of Mechanical Engineering,2015,51(13):45-52.
[5] IQBAL J,TSAGARAKIS N G,CALDWELL D G. Human hand compatible underactuated exoskeleton robotic system[J]. Electronics Letters,2014,50(7):494-496.
[6] LI Jiting,WANG Shuang,WANG Ju,et al. Development of a hand exoskeleton system for index finger rehabilitation[J]. Chinese Journal of Mechanical Engineering,2012,25(2):223-233.
[7] ZHANG Feng,LI Pengfeng,HOU Zenggou,et al. sEMG-based continuous estimation of joint angles of human legs by using BP neural network[J]. Neurocomputing,2012,78(1):139-148.
[8] SOEKADAR S R,BIRBAUMER N,SLUTZKY M W,et al. Brain machine interfaces in neurorehabilitation of stroke[J]. Neurobiology of disease,2015,83:172-179
[9] DONATI A R C,SHOKUR S,MORYA E,et al. Long-term training with a brain-machine interface-based gait protocol induces partial neurological recovery in paraplegic patients[J]. Scientific Reports,2016,6:30383.
[10] GOMEZ-RODRIGUEZ M,GROSSE-WENTRUP M,HILL J,et al. Towards brain-robot interfaces in stroke rehabilitation-[C]//IEEE International Conference on Rehabilitation Robo-tics,June 29-July 1,2011,Zurich,Switzerland,Piscataway:IEEE,2011:1-6.
[11] LI Yuanqing,PAN Jiahui,WANG Fei,et al. A hybrid BCI system combining P300 and SSVEP and its application to wheelchair control[J]. IEEE Transactions on Biomedical Engineering,2013,60(11):3156-3166.
[12] 唐智川,孙守迁,张克俊. 基于运动想象脑电信号分类的上肢康复外骨骼控制方法研究[J]. 机械工程学报,2017,53(10):60-69. TANG Zhichuang,SUN Shouqian,ZHANG Kejun. Research on the control method of an upper-limb rehabilitation exoskeleton based on classification of motor imagery EEG[J]. Journal of Mechanical Engineering,2017,53(10):60-69.
[13] NASIHATKON B,BOOSTANI R,JAHROMI M Z. Aneff-icient hybrid linear and kernel CSP approach for EEG feature extraction[J]. Neurocomputing,2009,73(1-3):432-437.
[14] LIU W,POKHAREL P P,PRINCIPE J C. Correntropy:Properties and applications in non-Gaussian signal process-ing[J]. IEEE Transactions on Signal Processing,2007,55(11):5286-5298.
[15] ARONSZAJN N. Theory of reproducing kernels[J]. Transactions of the American Mathematical Society,1950,68(3):337-404.
[16] DONG J,CHEN B,LU N,et al. Correntropy induced metric based common spatial patterns[C]//IEEE 27th International Workshop on. IEEE Machine Learning for Signal Processing,September 25-28,2017,Tokyo,Japan,Piscataway:IEEE,2017:1-6.
[17] BAARS B J,GAGE N M. Cognition,brain,and consciousness:Introduction to cognitive neuroscience[M]. Academic Press,2010.
[18] SUN Gufei,HU Jinglu,WU Gengfeng. A novel frequency band selection method for common spatial pattern in motor imagery based brain computer interface[C]//IEEE International Joint Conference on Neural Networks, July 18-23,2010,Barcelona,Spain,Piscataway:IEEE,2010:1-6.
[19] SCHNEIDER W,ESCHMAN A,ZUCCOLOTTO A. E-Prime[M]. Psychology Software Incorporated,2002.
[20] LOTTE F,GUAN C. Regularizing common spatial patterns to improve BCI designs:Unified theory and new algorithms[J]. IEEE Transactions on biomedical Engineering,2011,58(2):355-362.
[21] CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST),2011,2(3):1-27.

基于改进共空间模式与视觉反馈的闭环脑机接口

Closed Loop Brain Computer Interface Based on Improved Common Spatial Patterns and Visual Feedback

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价