Angle Estimation for Knee Joint Movement Based on PCA-RELM Algorithm

被引:20
作者
Deng, Yanxia [1 ]
Gao, Farong [1 ]
Chen, Huihui [1 ]
机构
[1] Hangzhou Dianzi Univ, Artificial Intelligence Inst, Hangzhou 310018, Peoples R China
来源
SYMMETRY-BASEL | 2020年 / 12卷 / 01期
基金
中国国家自然科学基金;
关键词
joint angle estimation; principal component analysis (PCA); regularized extreme learning machine (RELM); surface electromyogram (sEMG); error analysis; EXTREME LEARNING-MACHINE; REGRESSION; MODEL;
D O I
10.3390/sym12010130
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Surface electromyogram (sEMG) signals are easy to record and offer valuable motion information, such as symmetric and periodic motion in human gait. Due to these characteristics, sEMG is widely used in human-computer interaction, clinical diagnosis and rehabilitation medicine, sports medicine and other fields. This paper aims to improve the estimation accuracy and real-time performance, in the case of the knee joint angle in the lower limb, using a sEMG signal, in a proposed estimation algorithm of the continuous motion, based on the principal component analysis (PCA) and the regularized extreme learning machine (RELM). First, the sEMG signals, collected during the lower limb motion, are preprocessed, while feature samples are extracted from the acquired and preconditioned sEMG signals. Next, the feature samples dimensions are reduced by the PCA, as well as the knee joint angle system is measured by the three-dimensional motion capture system, are followed by the normalization of the feature variable value. The normalized sEMG feature is used as the input layer, in the RELM model, while the joint angle is used as the output layer. After training, the RELM model estimates the knee joint angle of the lower limbs, while it uses the root mean square error (RMSE), Pearson correlation coefficient and model training time as key performance indicators (KPIs), to be further discussed. The RELM, the traditional BP neural network and the support vector machine (SVM) estimation results are compared. The conclusions prove that the RELM method, not only has ensured the validity of results, but also has greatly reduced the learning train time. The presented work is a valuable point of reference for further study of the motion estimation in lower limb.
引用
收藏
页数:17
相关论文
共 38 条
[1]   Fractional Order Butterworth Filter: Active and Passive Realizations [J].
Ali, A. Soltan ;
Radwan, A. G. ;
Soliman, Ahmed M. .
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2013, 3 (03) :346-354
[2]  
[Anonymous], 2005, Int. J. Inf. Technol
[3]   EMG-Based Control of a Robot Arm Using Low-Dimensional Embeddings [J].
Artemiadis, Panagiotis K. ;
Kyriakopoulos, Kostas J. .
IEEE TRANSACTIONS ON ROBOTICS, 2010, 26 (02) :393-398
[4]   Normalised Mutual Information of High-Density Surface Electromyography during Muscle Fatigue [J].
Bingham, Adrian ;
Arjunan, Sridhar P. ;
Jelfs, Beth ;
Kumar, Dinesh K. .
ENTROPY, 2017, 19 (12)
[5]   Real-time myoprocessors for a neural controlled powered exoskeleton arm [J].
Cavallaro, Ettore E. ;
Rosen, Jacob ;
Perry, Joel C. ;
Burns, Stephen .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (11) :2387-2396
[6]   A Convenient and Robust Test to Quantify Interocular Suppression for Children With Amblyopia [J].
Chen, Hui ;
He, Zhifen ;
Xu, Jinling ;
Mao, Yu ;
Liang, Yunjie ;
Lin, Danli ;
Xu, Meiping ;
Dai, Zhiyue ;
Chen, Xiaoxin ;
Zhou, Jiawei ;
Yu, Xinping .
I-PERCEPTION, 2019, 10 (04)
[7]  
Chen HH, 2018, CHIN CONTR CONF, P5549, DOI 10.23919/ChiCC.2018.8482982
[8]  
Chen Jiangcheng, 2016, Journal of Xi'an Jiaotong University, V50, P61, DOI 10.7652/xjtuxb201606010
[9]   Prediction model for dynamic joint torque of lower limb with surface EMG [J].
Chen, Jiangcheng ;
Zhang, Xiaodong ;
Li, Rui ;
Shi, Qiangyong ;
Wang, He .
Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University, 2015, 49 (12) :26-33
[10]   An Entropy-Based Generalized Gamma Distribution for Flood Frequency Analysis [J].
Chen, Lu ;
Singh, Vijay P. ;
Xiong, Feng .
ENTROPY, 2017, 19 (06)