Development of a myoelectric interface for indirect hand grip force measurement and analysis /
Limb loss is a growing problem in Malaysia and the rest of the world due to the increasing number of industrial accidents, diseases and armed conflicts. After a tragic incident resulting in an amputation or paralysis, the disabled individual needs to be assisted with all possible technological means...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2012
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Limb loss is a growing problem in Malaysia and the rest of the world due to the increasing number of industrial accidents, diseases and armed conflicts. After a tragic incident resulting in an amputation or paralysis, the disabled individual needs to be assisted with all possible technological means to improve his quality of life. A cybernetic prosthesis is a device which can greatly assist individuals with hand disabilities by enabling them to have some of the hand capabilities of an able bodied individual. The central nervous system which consists of the brain and spine governs hand grip force and hand movement in the human body by spatial and temporal motor unit recruitments. Electromyogram (EMG) is an electrical biological signal that can be measured from the skin surface and consists of the summation of Motor Unit Action Potentials (MUAP). Hand grip strength, wrist extension and wrist flexion are hand functions which result from forearm muscle activity are used in a wide range of daily tasks. Extracting hand grip force and wrist angle information from forearm EMG signals is useful to be used as inputs for the control of cybernetic prostheses. By establishing the relationship between forearm EMG and hand grip force/wrist angles, the prosthetic hand can be controlled in a manner that is customized to an amputee's intent. As a matter of fact, there is none of the known research works that attempted to study the relationship between the EMG and the handgrip force at varying angles in the neural network context. In this research work, a myoelectric interface which consists of an electronic conditioning circuit to measure EMG signals and the software to record and process the EMG signals was developed. Experimental training and testing data sets from five subjects were collected to investigate the relationship between forearm EMG, hand grip force and wrist angle simultaneously. Artificial Neural Networks (ANN) were used to model the relationship in which the inputs are forearm EMGs and the outputs are hand grip force and wrist angle values. The training data sets were used to train the neural networks whereas the testing data sets were used to validate the performance of the trained neural networks. The ~ performances of the neural networks were evaluated by calculating the Mean Absolute Error (MAE) between the outputs of the neural network and the actual outputs. |
|---|---|
| Item Description: | Abstracts in English and Arabic. " A dissertation submitted in fulfilment of the requirement for the degree of Master of Science in Mechatronics Engineering."--On t.p. |
| Physical Description: | xvi, 118 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 101-106). |