Authors:
Edinson Porras
;
Lina Peñuela
and
Alexandra Velasco
Affiliation:
Universidad Militar Nueva Granada, Mechatronics Engineering Department, Bogota and Colombia
Keyword(s):
Electromyography, Knee Rehabilitation, Polynomial Adjustment, Locally Weighted Projection Regression.
Related
Ontology
Subjects/Areas/Topics:
Adaptive Signal Processing and Control
;
Engineering Applications
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Robotics and Automation
;
Signal Processing, Sensors, Systems Modeling and Control
Abstract:
Knee injuries are due to several causes and affect a large part of the population. In all of the cases, rehabilitation is required to recover the joint mobility and strength. In this context, the use of technology, especially the development of assistive devices may offer advantages to the patients, e.g. allow to perform correctly the exercises, adapt to the users’ needs and help to comply with the prescribed physical therapy. These devices may have specific requirements focused on not harming the patient. This is why control strategies are needed, and therefore feedback sensing is highly important. In this paper we present an algorithm to determine the knee joint angular position from surface Electromyography (EMG) measurements, using a curve fit from a polynomial adjustment method and a Locally Weighted Projection Regression (LWPR) method. We validate our approach, comparing the data obtained from the curve fitting with the measurements obtained with position sensors. In this way,
results show that indeed we can explain the joint angular position with the EMG data taken in knee flexion-extension motion, applying a polynomial adjustment approach and the LWPR method.
(More)