Artificial Neural Networks for Enhanced Exoskeleton Grip Movement
(2018) In Master's Theses in Mathematical Sciences FMAM05 20181Mathematics (Faculty of Engineering)
- Abstract
- The idea to artificially enhance our physical abilities has always fascinated humankind and over the cause of history it has resulted in countless important innovations such as wheelchairs and carbon-fiber-reinforced polymer leg prosthetics. By combining electronics and Artificial Intelligence the step towards artificially enhanced limbs has been greatly reduced. This master’s thesis describes the development of a Machine Learning solution to control an upper extremity exoskeleton. A Recurrent Neural Network is developed and trained on Electromyography data from the forearm. Two different networks and two data sets are tested. The results show that this approach is very promising for classification of grip movements if implemented... (More)
- The idea to artificially enhance our physical abilities has always fascinated humankind and over the cause of history it has resulted in countless important innovations such as wheelchairs and carbon-fiber-reinforced polymer leg prosthetics. By combining electronics and Artificial Intelligence the step towards artificially enhanced limbs has been greatly reduced. This master’s thesis describes the development of a Machine Learning solution to control an upper extremity exoskeleton. A Recurrent Neural Network is developed and trained on Electromyography data from the forearm. Two different networks and two data sets are tested. The results show that this approach is very promising for classification of grip movements if implemented correctly. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8964188
- author
- Horal, Malcolm LU
- supervisor
- organization
- course
- FMAM05 20181
- year
- 2018
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- AI, ML, ANN, RNN, Exoskeleton, Electromyography
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3365-2018
- ISSN
- 1404-6342
- other publication id
- 2018:E65
- language
- English
- id
- 8964188
- date added to LUP
- 2018-12-28 14:42:09
- date last changed
- 2019-07-12 10:04:06
@misc{8964188, abstract = {{The idea to artificially enhance our physical abilities has always fascinated humankind and over the cause of history it has resulted in countless important innovations such as wheelchairs and carbon-fiber-reinforced polymer leg prosthetics. By combining electronics and Artificial Intelligence the step towards artificially enhanced limbs has been greatly reduced. This master’s thesis describes the development of a Machine Learning solution to control an upper extremity exoskeleton. A Recurrent Neural Network is developed and trained on Electromyography data from the forearm. Two different networks and two data sets are tested. The results show that this approach is very promising for classification of grip movements if implemented correctly.}}, author = {{Horal, Malcolm}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Artificial Neural Networks for Enhanced Exoskeleton Grip Movement}}, year = {{2018}}, }