Muscle tone level classification based on upper-limb impedance model /
Many strategies have been developed by occupational and physical therapists for the assessment of upper-limb motor function or muscle tone of post-stroke patients or patients with physical limb disabilities. Estimation of patients' muscle tones allow proper prescription of therapy and determina...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2017
|
| Subjects: | |
| Online Access: | http://studentrepo.iium.edu.my/handle/123456789/5017 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Many strategies have been developed by occupational and physical therapists for the assessment of upper-limb motor function or muscle tone of post-stroke patients or patients with physical limb disabilities. Estimation of patients' muscle tones allow proper prescription of therapy and determination of physical recovery or recovery progress. Despite, having the appropriate skills, the therapist still face serious challenges in estimating appropriately the patients' muscle tone and quantifying, continuously, the recovery progress. Moreover, the therapy has become more costly and time consuming since the patients are required to have face-to-face contact with the therapist over a long period of time. By deploying robot-assisted rehabilitation therapy, some of these problems have been addressed but the aspect of proper estimation and assessment of patient muscle tone levels and recovery progress during rehabilitation therapy still remain a big challenge. Recent studies have established link between muscle tone and upper-limb mechanical impedance, however the development of an adequate estimation algorithm and setup for estimation of patients' upper-limb impedance parameters and the prediction of physical recovery level in a more efficient, objective and consistent manner is still a subject of many research works. This study proposes an appropriate strategy for the estimation of upper-limb mechanical impedance parameters as a mean for the prediction and assessment of subjects' muscle tone level. The human upper-limb is modeled as a mass-spring-damper system and represented as an Auto Regressive eXogenous (ARX) dynamic equation for the estimation of upper-limb mechanical impedance parameters using an online Recursive Least Squares (RLS) estimator method. The estimated impedance parameters are then fed as inputs to a trained Artificial Neural Network (ANN) which is used to predict, online, the subjects' muscle tone level during rehabilitation exercise. To verify the accuracy of the estimation and prediction method, five healthy subjects were asked to go through specific and controlled extension range of motion tasks. Both simulation and experimental results show that the upper-limb impedance parameters can be estimated to a good accuracy level, while the subjects' muscle tone level can be reliably predicted with high accuracy. |
|---|---|
| Physical Description: | xv, 83 leaves : ill. ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 71-75). |