中国组织工程研究

中国组织工程研究 ›› 2019, Vol. 23 ›› Issue (32): 5164-5169.doi: 10.3969/j.issn.2095-4344.1493

• 数字化骨科 digital orthopedics • 上一篇    下一篇

一种基于表面肌电信号及三轴加速度信号的步态识别方法

郝静涵，杨  鹏，陈玲玲，耿艳利   

  1. 河北工业大学，人工智能与数据科学学院，天津市  300130
  • 出版日期:2019-11-18 发布日期:2019-11-18
  • 通讯作者: 陈玲玲，博士，副教授，河北工业大学，人工智能与数据科学学院，天津市 300130
  • 作者简介:郝静涵，男，1994年生，河北省高碑店市，汉族，河北工业大学在读硕士，主要从事肌电信号分析及模式识别研究。
  • 基金资助:

    国家自然科学基金(61803143)，项目负责人：耿艳利|国家自然科学基金(61703135)，项目负责人：陈玲玲|河北省自然科学基金(F2017202119)，项目负责人：陈玲玲

A gait recognition approach based on surface electromyography and triaxial acceleration signals

Hao Jinghan, Yang Peng, Chen Lingling, Geng Yanli   

  1. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China
  • Online:2019-11-18 Published:2019-11-18
  • Contact: Chen Lingling, MD, Associate professor, School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China
  • About author:Hao Jinghan, Master candidate, School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China
  • Supported by:

    the National Natural Science Foundation of China, No. 61803143 (to GYL), the National Natural Science Foundation of China, No. 61703135 (to CLL)| the Natural Science Foundation of Hebei Province of China, No. F2017202119 (to CLL)

PDF

89

摘要：

文章快速阅读：


文题释义：
表面肌电信号：是一种生物电信号，是人体肌肉在运动时产生的电位在皮肤表面的叠加。表面肌电信号产生于大脑运动意图产生之后，肌肉真正收缩产生之前，是一种十分接近于人体运动初衷的信号，被广泛地应用于康复、医疗和体育等研究领域。
隐马尔科夫模型：是一种概率模型，对时序信号优异的建模性能，其能表示各个隐藏状态之间转换的概率，和观测状态在每个隐藏状态下的概率分布情况。
 
摘要
背景：由于频发的各种意外灾害以及身体疾病，使得相当数量的人丧失了行走能力，如何通过对人体的动作识别，设计外骨骼助行器用于恢复这些患者的行走能力，已经逐渐成为康复工程领域的热门课题。
目的：在分类器层面对表面肌电信号及三轴加速度信号进行融合，提高人体步态辨识识别率。
方法：提出了一种基于表面肌电信号和三轴加速度信号相结合的方法来识别5种不同的日常基本步态模式，包括平地行走、上楼梯、下楼梯、上斜坡和下斜坡。采集人体下肢5通道表面肌电信号及大腿处和小腿处三轴加速度信号，将信号预处理后进行特征提取，构建基于双流隐马尔科夫模型的分类器对5种日常基本步态模式进行分类识别研究。
结果与结论：①实验对5种基本步态模式进行了识别，实验平均识别率为94.32%，较仅采用表面肌电信号信号进行识别的准确率(平均90.17%)高出4.15%，并且较仅采用三轴加速度信号的识别率(平均84.72%)高出9.60%；②结果表明，将表面肌电信号信号与加速度信号相结合，可以获得更有用的运动信息，有助于提高离线分析下的步态识别精度。


ORCID: 0000-0003-0384-6557(郝静涵)

关键词: 步态识别, 表面肌电信号, 加速度信号, 隐马尔科夫模型, 外骨骼助行器, 国家自然科学基金

Abstract:

BACKGROUND: Due to frequent accidents and physical diseases, a large number of people have lost the ability to walk. How to gradually restore the walking ability of these patients through motion recognition of the human body with an exoskeleton walker has gradually become a hot topic in the field of medical rehabilitation engineering.
OBJECTIVE: To improve the recognition rate of human gait by fusion of surface electromyography signals and triaxial acceleration signals at classifier level.
METHODS: An approach based on combining surface electromyography signals and triaxial acceleration signals was proposed to recognize five different kinds of basis daily gait patterns, including walking on the ground, going up stairs, going down stairs, going up slope and going down slope. The surface electromyography signals of five channels in the lower limbs and triaxial acceleration signals at the thighs and calves were collected. After signal pre-processing, the features of fusion signals were extracted. A classifier based on two-stream Hidden Markov Model was constructed to train the classifier. The classifier was trained and tested with test set to obtain the recognition accuracy.
RESULTS AND CONCLUSION: (1) Five basic gait patterns were identified. The experiment obtained an average recognition accuracy of 94.32%, which was 4.15% higher than the accuracy by adopting surface electromyography signal only (average 90.17%), and 9.60% higher than the accuracy by adopting acceleration signal only (average 84.72%). (2) The results showed that more useful movement information could be obtained by combining surface electromyography signal and acceleration signal, which can help improve the recognition accuracy.

Key words: gait recognition, surface electromyogram, acceleration signal, hidden Markov model, exoskeleton walker, National Natural Science Foundation of China

中图分类号: