[1]潘红光,张 奇,米文毓,等.基于长短期记忆网络的解码器设计及闭环脑机接口系统构建[J].西安科技大学学报,2019,(06):1057-1064.
 PAN Hong-guang,ZHANG Qi,MI Wen-yu,et al.LSTM-based decoder design andclosed-loop BMI system formulation[J].Journal of Xi'an University of Science and Technology,2019,(06):1057-1064.
点击复制

基于长短期记忆网络的解码器设计及闭环脑机接口系统构建(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2019年06期
页码:
1057-1064
栏目:
出版日期:
2019-12-20

文章信息/Info

Title:
LSTM-based decoder design andclosed-loop BMI system formulation
文章编号:
1672-9315(2019)06-1057-08
作者:
潘红光1张 奇1米文毓1马 彪2
(1.西安科技大学 电气与控制工程学院,陕西 西安 710054; 2.鄂尔多斯市神东工程设计有限公司,鄂尔多斯 017000)
Author(s):
PAN Hong-guang1ZHANG Qi1MI Wen-yu1MA Biao2
(1.College of Electrical and Control Engineering,Xi'an University of Science and Technology,Xi'an 710054,China; 2.Ordos Shendong Engineering Design Co.,Ltd.,Ordos 017000,China)
关键词:
闭环脑机接口 解码器 长短期记忆网络 无模型控制
Keywords:
closed-loop brain-machine interface decoder long short-term memory networks model-free control
分类号:
TP 13
文献标志码:
A
摘要:
随着脑机接口技术的发展,该技术在残疾人肢体功能恢复等方面应用越来越广泛。首先,在简介经典单关节信息传输模型基础上,设计并训练基于长短期记忆网络的解码器,代替原有脊椎电路通路将大脑信号传递给假肢; 其次,为了在感觉反馈通路缺失时,仍能准确地恢复肢体运动功能,结合基于无模型控制策略设计的辅助控制器,构建闭环脑机接口系统,实现恢复关节活动障碍者缺失的感觉反馈通路从而实现跟踪期望轨迹的目的。由仿真可知,基于长短期记忆网络设计的解码器的离线解码效果良好。构建的闭环脑机接口系统对期望轨迹的跟踪以及缺失信息通路的恢复的结果验证了无模型控制辅助控制器良好的控制性能以及构建的闭环脑机接口系统的有效性。
Abstract:
With the development of brain-machine interface technology,the technology has been widely used in the restoration of limb motor function of disabled people.Firstly,referring to the classical single joint information transfer model,this paper designs and trains a decoder based on the long short-term memory network,which is used to replace the spinal circuit pathway to transmit the brain signal to the prosthesis.Secondly,in order to make up for the absence feedback channel and to restore limb movement function accurately,the designed decoder is combined with an auxiliary controller based on model-free control strategy to build a closed-loop brain-machine interface system which can restore the absence feedback path and achieve the purpose of tracking expected trajectory.Simulation results show that the decoder designed by the long short-term memory network has a good off-line decoding effect,that is,the designed decoder can well restore the absence spinal circuit channel.The results of tracking the desired trajectory and of restoring the absence information path of the constructed closed-loop brain-machine interface system verify the good control performance of the model-free control strategy and the effectiveness of the constructed closed-loop brain-machine interface system.

参考文献/References:

[1] Pan H G,Ding B C,Zhong W,et al.Designing closed-loop brain-machine interfaces with network of spiking neurons using MPC strategy[C]//American Control Conference.IEEE,2016:2543-2548. [2]Iturrate I,Antelis J M,Kubler A,et al.A noninvasive brain-actuated wheelchair based on a P300 neurophysiological protocoland automated navigation[J].IEEE Transactions on Robotics,2009,25(3):614-627. [3]琚 芬,赵晨光,袁 华,等.脑机接口在康复医学中的应用进展[J].中国康复,2017,32(6):508-511. JU Fen,ZHAO Chen-guang,YUAN Hua,et al.Application progress of brain-computer interface in rehabilitation medicine[J].China Re-habilitation,2017,32(6):508-511. [4]Shi M H,Zhou C L,Xie J,et al.Electroencephalogram-based brain-computer interface for the Chinese spelling system:a survey[J].Frontiers of Information Technology & Electronic Engineering,2018,19(3):423-436. [5]Suyama T.A network-type brain-machine interface to support activities of daily living[J].Ieice Transactions on Communications,2016,99(9):1930-1937. [6]孙京诰,戚 川,潘红光.基于数据驱动的闭环脑机接口设计[J].华东理工大学学报(自然科学版),2017,43(5):655-661. SUN Jing-hao,QI Chuan,PAN Hong-guang.Design of closed-loop brain-machine interface based on data-driven[J].Journal of East China University of Science and Technology(Natural Science Edition),2017,43(5):655-661. [7]Golub M D,Yu B M,Schwartz A B,et al.Motor cortical control of movement speed with implications for brain-machine interface control[J].Journal of Neurophysiology,2014,112(2):411-429. [8]Shanechi M M,Orsborn A L,Moorman H G,et al.Rapid control and feedback rates enhance neuroprosthetic control[J].Nature Communications,2017(8):13825. [9]潘家辉,冯 宝.脑机接口中脑电信号的特征提取和模式分类[J].计算机系统应用,2015,24(8):268-272. PAN Jia-hui,FENG Bao.Feature extraction and pattern classification of EEG signals in brain-machine interface[J].Computer System Applications,2015,24(8):268-272. [10]Wodlinger B,Downey J E,Tyler-Kabara E C,et al.Ten-dimensional anthropomorphic arm control in a human brain?machine interface:difficulties,solutions,and limitations[J].Journal of Neural Engineering,2015,12(1):016011. [11]Hong Z,Yanxin W,Changcheng W,et al.Closed-loop hybrid gazebrain-machine interface based robotic arm control with augmented reality feedback[J].Frontiers in Neurorobotics,2017,11(60):60-73. [12]Orsborn A.Closed-loop design of brain-machine interface systems[D].Berkeley San Francisco:University of California-Berkeley,2013. [13]Hortal E,Planelles D,Costa A,et al.SVM-based brain-machine interface for controlling a robot arm through four mental tasks[J].Neurocomputing,2015,151:116-121. [14]Abdullah,Subari,Loong,et al.Analysis of effective channel placement for an EEG-based biometric system[C]//Biomedical Engineering & Sciences.IEEE,2011:303-306. [15]Bullock D,Cisek P,Grossberg S.Cortical networks for control of voluntary arm movements under variable force conditions[J].Cerebral Cortex,1998,8(1):48-62. [16]Kumar G,Schieber M H,Thakor N V,et al.Designing closed-loop brain-machine interfacesusing optimal receding horizoncontrol[C]//American Control Conference.IEEE,2013:5029-5034. [17]Dangi S,Gowda S,Heliot R,et al.Adaptive kalman filtering for closed-loop brain-machine interface systems[C]//International IEEE/EMBS Conference on Neural Engineering.IEEE,2011:609-612. [18]Sussillo D,Nuyujukian P,Fan J M,et al.A recurrent neural network for closed-loop intracortical brain machine interface decoders[J].Journal of Neural Engineering,2012,9(2):026027. [19]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780. [20]Gao L,Zhao G,Zhang H W,et al.Video captioning with attention-based LSTM and semantic consistency[J].IEEE Transactions on Multimedia,2017,9(19):2045-2055. [21]李伟山,王 琳,卫 晨.LSTM在煤矿瓦斯预测预警系统中的应用与设计[J].西安科技大学学报,2018(6):1027-1035. LI Wei-shan,WANG Lin,WEI Chen.Application and design of LSTM in coal mine gas prediction and warning system[J].Journal of Xi'an University of Science and Technology,2018(6):1027-1035. [22]Hong Z,Yanxin W,Changcheng W,et al.Closed-loop hybrid gaze brain-machine interface based robotic arm control with augmented reality feedback[J].Frontiers in Neurorobotics,2017,11:60-73. [23]潘红光,米文毓,邓 军,等.基于改进单关节信息传输模型的闭环脑机接口系统设计[J/OL].控制理论与应用,2019-06-11. PAN Hong-guang,MI Wen-yu,DENG Jun,et al.Closed-loop brain-machine interface system design based on improved single-joint information transmission model[J/OL].Control Theory & Application,2019-06-11. [24]Hou Z,Huang W.The model-free learning adaptive control of a class of nonlinear discrete-time systems[J].IFAC Proceedings Volumes,1998,15(6):893-899. [25]Li M,Branson D,Jian S D,et al.Model-free control for continuum robots based on an adaptive kalman filter[J].IEEE/ASME Transactions on Mechatronics,2018,1(23):286-297.

备注/Memo

备注/Memo:
收稿日期:2019-04-22 责任编辑:高 佳
基金项目:国家自然科学基金(61603295); 中国博士后基金(2017M623207); 陕西省自然科学基础研究计划(2018JM6003); 西安科技大学优秀青年科技基金(2018YQ2-07)
通信作者:潘红光(1983-),男,山东临沂人,博士,讲师,E-mail:hongguangpan@163.com
更新日期/Last Update: 2019-12-20