EEG and sEMG Decoding of Gait Spatiotemporal Parameters Based on Bidirectional Long Short-Term Memory Neural Network

WEI Pengna; MA Pengcheng; ZHANG Jinhua; HONG Jun

doi:10.7652/xjtuxb202209015

您当前的位置：

首页 >

文章列表页 >

EEG and sEMG Decoding of Gait Spatiotemporal Parameters Based on Bidirectional Long Short-Term Memory Neural Network

更新时间：2025-07-09

- EEG and sEMG Decoding of Gait Spatiotemporal Parameters Based on Bidirectional Long Short-Term Memory Neural Network
- Vol. 56, Issue 9, Pages: 142-150(2022)
- 作者机构：
  
  西安交通大学现代设计与转子轴承系统教育部重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202209015
  CLC： TP242
- Online First：10 September 2022，
  
  Published：2022
- 稿件说明：
移动端阅览
WEI Pengna, MA Pengcheng, ZHANG Jinhua, et al. EEG and sEMG Decoding of Gait Spatiotemporal Parameters Based on Bidirectional Long Short-Term Memory Neural Network[J]. 2022, 56(9): 142-150.
DOI：

WEI Pengna, MA Pengcheng, ZHANG Jinhua, et al. EEG and sEMG Decoding of Gait Spatiotemporal Parameters Based on Bidirectional Long Short-Term Memory Neural Network[J]. 2022, 56(9): 142-150. DOI： 10.7652/xjtuxb202209015.

摘要

针对脑电(EEG)信号对连续步态轨迹解码结果与实际轨迹相关性低的问题

提出一种基于双向长短时记忆(BiLSTM)神经网络的步态参数解码方法。首先

构建基于双向长短时记忆神经网络的步态时空参数解码模型

根据脑肌电信号特性设计解码模型的超参数; 其次

同步采集脑电、下肢运动相关肌肉的表面肌电信号(sEMG)和下肢关节运动信号

并对脑电和表面肌电信号的步态相关特征进行分析; 然后

以多通道脑电和下肢运动相关表面肌电信号作为解码模型的输入

自动提取脑肌电融合信号中步态相关特征并构建膝踝关节运动轨迹与特征之间的非线性回归模型; 最后

以多通道脑电作为解码模型的输入

构建步态相关脑电信号和表面肌电信号之间的非线性回归模型。实验结果表明:所提方法与传统支持向量机方法相比

对踝关节解码轨迹与实测轨迹形状相似性Pearson相关系数提高了0.12; 与单独采用脑电、表面肌电信号和脑肌电信号平均绝对值特征融合信号进行解码方法相比

对踝关节解码轨迹与实测轨迹形状相似性Pearson相关系数分别提高了0.81、0.19和0.63。该方法可实现从脑电信号中对部分表面肌电信号波形的解码

解码波形和实测波形的平均Pearson相关系数值接近0.5

证明从脑电信号中可解码出肌肉通道的表面肌电信号波形

为下肢外骨骼主动连续控制的应用提供了新思路。

Abstract

To solve the problem of low correlation between continuous gait trajectory decoding results and actual trajectory by electroencephalography(EEG)signals

a gait parameter decoding method based on bidirectional long short-term memory(BiLSTM)neural network is proposed. Firstly

a gait spatiotemporal parameter decoding model based on this neural network is constructed

and the hyperparameters of the decoding model are designed according to the characteristics of EEG and surface electromyography(sEMG). Secondly

EEG

lower limb movement-related sEMG and lower limb joint movement signals are collected synchronously

and gait features of EEG and sEMG signals are analyzed. Thirdly

multi-channel EEG and lower limb movement-related sEMG signals are used as input of the decoding model

and gait related features are extracted automatically from EEG and sEMG fusion signals

and the nonlinear regression model between ankle joint motion and gait related features is constructed. Finally

a nonlinear regression model between gait related EEG signals and sEMG signals is constructed with multi-channel EEG as the input of the decoding model. The results show that compared with traditional support vector machines

the Pearson correlation coefficient of shape similarity between decoded trajectory and measured trajectory is improved by 0.12. Compared with the decoding methods using EEG

sEMG and fusion average absolute value of EEG-sEMG

the proposed method improves the Pearson correlation coefficient of shape similarity between decoded trajectory and measured trajectory by 0.81

0.19 and 0.63

respectively. Our decoding method can realize decoding of part of sEMG waveform

the average Pearson correlation coefficient of decoded waveform and measured waveform is close to 0.5. It shows that the sEMG signals can be decoded from EEG signal which provides a new idea for the application of active continuous control of lower extremity exoskeleton

关键词

Keywords

references

YOUNG A J, FERRIS D P. State of the art and future directions for lower limb robotic exoskeletons [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25(2): 171-182.

KAPSALYAMOV A, JAMWAL P K, HUSSAIN S, et al. State of the art lower limb robotic exoskeletons for elderly assistance [J]. IEEE Access, 2019, 7: 95075-95086.

TARIQ M, TRIVAILO P M, SIMIC M. EEG-based BCI control schemes for lower-limb assistive-robots [J]. Frontiers in Human Neuroscience, 2018, 12: 312.

陈朝峰. 穿戴式下肢外骨骼系统设计与交互控制策略研究 [D]. 哈尔滨: 哈尔滨工业大学, 2020.

GORDLEEVA S Y, LOBOV S A, GRIGOREV N A, et al. Real-time EEG-EMG human-machine interface-based control system for a lower-limb exoskeleton [J]. IEEE Access, 2020, 8: 84070-84081.

杨灿军, 彭桢哲, 徐铃辉, 等. 柔性膝关节保护外骨骼及其行走助力方法设计 [J]. 浙江大学学报(工学版), 2021, 55(2): 213-221.

YANG Canjun, PENG Zhenzhe, XU Linghui, et al. Design of flexible knee-joint protection exoskeleton and walking assistance method [J]. Journal of Zhejiang University(Engineering Science), 2021, 55(2): 213-221.

WINTER C, KERN F, GALL D, et al. Immersive virtual reality during gait rehabilitation increases walking speed and motivation: a usability evaluation with healthy participants and patients with multiple sclerosis and stroke [J]. Journal of NeuroEngineering and Rehabilitation, 2021, 18(1): 68.

陈超强, 蒋磊, 王恒. 基于SAE和LSTM的下肢外骨骼步态预测方法 [J]. 计算机工程与应用, 2019, 55(12): 110-116, 154.

CHEN Chaoqiang, JIANG Lei, WANG Heng. Gait prediction method of lower extremity exoskeleton based on SAE and LSTM neural network [J]. Computer Engineering and Applications, 2019, 55(12): 110-116, 154.

RODRÍGUEZ-FERNÁNDEZ A, LOBO-PRAT J, FONT-LLAGUNES J M. Systematic review on wearable lower-limb exoskeletons for gait training in neuromuscular impairments [J]. Journal of NeuroEngineering and Rehabilitation, 2021, 18(1): 22.

郝静涵. 基于SEMG信号及加速度信号的步态辨识研究 [D]. 天津: 河北工业大学, 2019.

郭浩. 基于EMG的人体下肢运动意图感知与预测研究 [D]. 哈尔滨: 哈尔滨工业大学, 2019.

李梦瑶. 基于多源神经信号融合的人体运动意图识别研究 [D]. 北京: 中国科学院大学, 2021.

刘笃信. 下肢外骨骼机器人多模融合控制策略研究 [D]. 深圳: 中国科学院大学(中国科学院深圳先进技术研究院), 2018.

NAKAGOME S, LUU T P, HE Yongtian, et al. An empirical comparison of neural networks and machine learning algorithms for EEG gait decoding [J]. Scientific Reports, 2020, 10(1): 4372.

FITZSIMMONS N A, LEBEDEV M A, PEIKON I D, et al. Extracting kinematic parameters for monkey bipedal walking from cortical neuronal ensemble activity [J]. Frontiers in Integrative Neuroscience, 2009, 3: 3.

YI Chunzhi, JIANG Feng, BHUIYAN M Z A, et al. Smart healthcare-oriented online prediction of lower-limb kinematics and kinetics based on data-driven neural signal decoding [J]. Future Generation Computer Systems, 2021, 114: 96-105.

JIA LU, AI Qingsong, MENG Wei, et al. Individualized gait trajectory prediction based on fusion LSTM networks for robotic rehabilitation training [C]∥2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics(AIM). Piscataway, NJ, USA: IEEE, 2021: 988-993.

DELORME A, MAKEIG S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis [J]. Journal of Neuroscience Methods, 2004, 134(1): 9-21.

CHOI J, KIM H. Real-time decoding of EEG gait intention for controlling a lower-limb exoskeleton system [C]∥2019 7th International Winter Conference on Brain-Computer Interface(BCI). Piscataway, NJ, USA: IEEE, 2019: 1-3.

GWIN J T, GRAMANN K, MAKEIG S, et al. Electrocortical activity is coupled to gait cycle phase during treadmill walking [J]. NeuroImage, 2011, 54(2): 1289-1296.

WEI Pengna, ZHANG Jinhua, WANG Baozeng, et al. Surface electromyography and electroencephalogram-based gait phase recognition and correlations between cortical and locomotor muscle in the seven gait phases [J]. Frontiers in Neuroscience, 2021, 15: 607905.

PRESACCO A, GOODMAN R, FORRESTER L, et al. Neural decoding of treadmill walking from noninvasive electroencephalographic signals [J]. Journal of Neurophysiology, 2011, 106(4): 1875-1887.

SAXENA M, GUPTA A. Exploration of temporal and spectral features of EEG signals in motor imagery tasks [C]∥2021 International Conference on Communication Systems Networks(COMSNETS). Piscataway, NJ, USA: IEEE, 2021: 736-740.

SORIANO-SEGURA P, IANEZ E, ORTIZ M, et al. Detection of the intention of direction changes during gait through EEG signals [J]. International Journal of Neural Systems, 2021, 31(11): 2150015.

WEI Pengna, ZHANG Jinhua, TIAN Feifei, et al. A comparison of neural networks algorithms for EEG and sEMG features based gait phases recognition [J]. Biomedical Signal Processing and Control, 2021, 68: 102587.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Feature Exaction and Classification of Attention Related Electroencephalographic Signals Based on Sample Entropy

Automatic Gesture Recognition with Surface Electromyography Signal

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

Mechanism and Optimal Control Strategy for Hysteresis in Rapid Dehumidification Response of Indirect Thermal Systems in Electric Vehicles

Related Author

燕楠

王珏

魏娜

宗良

赵诗琪 1

吴旭洲 1

Related Institution

Key Laboratory of Biomedical Information Engineering of Education Ministry, Xi'an Jiaotong University

School of Life Science and Technology, Xi’an Jiaotong University

Key Laboratory of Biomedical Information Engineering of Ministry of Education, Xi’an Jiaotong University

National Engineering Research Center for Healthcare Devices

⁰