Development of EMG based continuous thumb-tip force model for prostheses design /
Human hand functions range from precise-minute handling to heavy and robust movements. Remarkably, 50 percent of all hand functions are made possible by the thumb. Therefore, developing an artificial thumb which can mimic the actions of a real thumb precisely is a major achievement. Most of the deve...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Gombak, Selangor :
Kuliyyah of Engineering, International Islamic University Malaysia,
2016
|
| Subjects: | |
| Online Access: | http://studentrepo.iium.edu.my/handle/123456789/4620 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| LEADER | 040510000a22003010004500 | ||
|---|---|---|---|
| 008 | 171228t2016 my a g m 000 0 eng d | ||
| 040 | |a UIAM |b eng | ||
| 041 | |a eng | ||
| 043 | |a a-my--- | ||
| 050 | |a QP321 | ||
| 100 | 1 | |a Abdul Rahman | |
| 245 | 1 | |a Development of EMG based continuous thumb-tip force model for prostheses design / |c by Abdul Rahman | |
| 260 | |a Gombak, Selangor : |b Kuliyyah of Engineering, International Islamic University Malaysia, |c 2016 | ||
| 300 | |a xiv, 111 leaves : |b ill. ; |c 30cm. | ||
| 500 | |a Abstracts in English and Arabic. | ||
| 500 | |a "A thesis submitted in fulfilment of the requirement for the degree of Master of Science in (Mechatronics Engineering)." --On t.p. | ||
| 502 | |a Thesis (MSMCT)--International Islamic University Malaysia, 2016. | ||
| 504 | |a Includes bibliographical references (leaves 89-94). | ||
| 520 | |a Human hand functions range from precise-minute handling to heavy and robust movements. Remarkably, 50 percent of all hand functions are made possible by the thumb. Therefore, developing an artificial thumb which can mimic the actions of a real thumb precisely is a major achievement. Most of the development in this area is based on discontinuous thumb position models, which makes it challenging to recreate several of the most important functions of the thumb and also does not result in total imitation. This work looks into the classification of Electromyogram (EMG) signals from thumb muscles for the prediction of thumb force and angle during flexion motion. For this purpose, an experimental setup is developed to measure the thumb angle and force throughout the range of flexion and simultaneously gather the EMG signals. A 'piecewise- discretization' approach is used for continuous angle prediction, where the full motion is divided into four segments or classes. For variation in force, the experimental setup is designed to accommodate different weight sets which require application of different thumb-tip force values from the thumb. The EMG signals are taken from four different muscles that are most engaged in the flexion motion. These are the Opponens Pollicis, Flexor Pollicis Brevis, Extensor Pollicis and the First Dorsal Interosseous. Fifteen different features of the time domain and six different features of the frequency domain are extracted from the EMG signals for classification and the most suitable feature set is determined and applied to different classifiers. Before classification, a suitable and appropriate feature set is built that consists of the most contributing and determinant features of the signals. Next, the feature set is applied to different classifiers in different combinations. Through an analysis of the results, the best feature set and best classifier is determined for the prediction of thumb angle and force. Different variations in the division of angle and force classes were also tried and the most suitable turned out to be four angle segments with three force/weight classes. Breaking away from previous researches, the frequency-domain features performed better than the time-domain features, with the best feature combination turning out to be MDF-MNF-MNP. As for the classifiers, the Support Vector Machine proved to be the most accurate classifier giving about 70% accuracy for both angle and force classification and close to 50% for joint angle-force classification. | ||
| 596 | |a 1 | ||
| 655 | 7 | |a Theses, IIUM local | |
| 690 | |a Dissertations, Academic |x Department of Mechatronics Engineering |z IIUM | ||
| 710 | 2 | |a International Islamic University Malaysia. |b Department of Mechatronics Engineering | |
| 856 | 4 | |u http://studentrepo.iium.edu.my/handle/123456789/4620 | |
| 900 | |a sbh-lfr | ||
| 999 | |c 436778 |d 469462 | ||
| 952 | |0 0 |6 T QP 000321 A136D 2016 |7 0 |8 THESES |9 761324 |a IIUM |b IIUM |c MULTIMEDIA |g 0.00 |o t QP 321 A136D 2016 |p 11100352221 |r 2018-03-09 |t 1 |v 0.00 |y THESIS | ||
| 952 | |0 0 |6 TS CDF QP 321 A136D 2016 |7 0 |8 THESES |9 855079 |a IIUM |b IIUM |c MULTIMEDIA |g 0.00 |o ts cdf QP 321 A136D 2016 |p 11100352222 |r 2018-03-09 |t 1 |v 0.00 |y THESISDIG | ||