Citation: Li, Z.; Gao, L.; Lu, W.;
Wang, D.; Cao, H.; Zhang, G.
Estimation of Knee Extension Force
Using Mechanomyography Signals
Based on GRA and ICS-SVR. Sensors
2022, 22, 4651. https://doi.org/
10.3390/s22124651
Academic Editors: Enrico Vezzetti,
Gabriele Baronio, Domenico
Speranza, Luca Ulrich and Andrea
Luigi Guerra
Received: 6 April 2022
Accepted: 15 June 2022
Published: 20 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Estimation of Knee Extension Force Using Mechanomyography
Signals Based on GRA and ICS-SVR
Zebin Li
1,2,3,
*
, Lifu Gao
1,2
, Wei Lu
1,2,
*, Daqing Wang
1
, Huibin Cao
1
and Gang Zhang
3
1
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences,
Hefei 230031, China; lifugao@iim.ac.cn (L.G.); dqwang@mail.ustc.edu.cn (D.W.); hbcao@iim.ac.cn (H.C.)
2
Department of Science Island, University of Science and Technology of China, Hefei 230026, China
3
School of Electrical and Photoelectric Engineering, West Anhui University, Lu’an 237012, China;
zhanggang@wxc.edu.cn
* Correspondence: robotzebinli@foxmail.com (Z.L.); lw9296@mail.ustc.edu.cn (W.L.)
Abstract:
During lower-extremity rehabilitation training, muscle activity status needs to be monitored
in real time to adjust the assisted force appropriately, but it is a challenging task to obtain muscle
force noninvasively. Mechanomyography (MMG) signals offer unparalleled advantages over sEMG,
reflecting the intention of human movement while being noninvasive. Therefore, in this paper,
based on MMG, a combined scheme of gray relational analysis (GRA) and support vector regression
optimized by an improved cuckoo search algorithm (ICS-SVR) is proposed to estimate the knee joint
extension force. Firstly, the features reflecting muscle activity comprehensively, such as time-domain
features, frequency-domain features, time–frequency-domain features, and nonlinear dynamics
features, were extracted from MMG signals, and the relational degree was calculated using the GRA
method to obtain the correlation features with high relatedness to the knee joint extension force
sequence. Then, a combination of correlated features with high relational degree was input into
the designed ICS-SVR model for muscle force estimation. The experimental results show that the
evaluation indices of the knee joint extension force estimation obtained by the combined scheme of
GRA and ICS-SVR were superior to other regression models and could estimate the muscle force
with higher estimation accuracy. It is further demonstrated that the proposed scheme can meet the
need of muscle force estimation required for rehabilitation devices, powered prostheses, etc.
Keywords:
muscle force estimation; MMG; gray relational analysis; machine learning; improved
cuckoo search algorithm
1. Introduction
The central nervous system quantitatively controls force production of the skeletal
muscles through the successive recruitment of motor units (MUs) [
1
]. These forces con-
tribute to the generation of the forces required to perform various movements and to
interact with the external environment. The skeletal muscles, as the power source of the
motor system, work together with the bones and joints to accomplish basic limb movements
such as standing, sitting, walking, and jumping, as well as complex movements, under the
innervation of the nervous system. Although these behaviors do not directly affect people’s
survival, they are directly related to living independently and autonomously.
In the real world, common muscular and neurological disorders, such as stroke and
hemiplegia, as well as cumulative diseases such as arthritis, lead to movement problems
in the skeletal muscle system and severely affect the body’s ability to move freely [
2
].
Rehabilitation with assistive devices has received increasing attention for helping these
patients regain their ability to live independently and improve their standard of living.
Some rehabilitation auxiliary devices in structured environments are able to obtain
kinematic information about the human body during limb movement through sensors or
the mechanical principle of the device itself to achieve simple repetitive tasks [
3
]. However,
Sensors 2022, 22, 4651. https://doi.org/10.3390/s22124651 https://www.mdpi.com/journal/sensors
