Abstract
A large number of amputee patients doesn't use their myoelectric prosthesis, mainly due to the limited functionality of the prosthesis.
The aim of this study was to investigate if it is possible to distinguish 8 different contractions by using multi-electrode sEMG.
We analysed sEMG signals of a grid of 40 and 30 electrodes from 10 healthy subjects and 1 amputee patient respectively during 8 different isometric movements of the wrist and fingers and classified them with a nearest neighbour classifier.
The results were very promising: over 99.5% of the movements were correctly classified and reducing the number of electrodes to 20 and 10 electrods only decreases the performance with 0.05 and 0.18%.
Original language | Undefined |
---|---|
Title of host publication | Proceedings of the 4th Annual symposium of the IEEE-EMBS Benelux Chapter |
Editors | P.H. Veltink, W. Eberle |
Place of Publication | Enschede |
Publisher | University of Twente |
Pages | 68-68 |
Number of pages | 1 |
ISBN (Print) | 978-90-365-2933-4 |
Publication status | Published - 9 Nov 2009 |
Event | 4th Annual Symposium of the Benelux Chapter of the IEEE Engineering in Medicine and Biology Society (IEEE-EMBS Benelux) 2009 - University of Twente, Enschede, Netherlands Duration: 9 Nov 2009 → 10 Nov 2009 Conference number: 4 |
Publication series
Name | |
---|---|
Publisher | University of Twente |
Conference
Conference | 4th Annual Symposium of the Benelux Chapter of the IEEE Engineering in Medicine and Biology Society (IEEE-EMBS Benelux) 2009 |
---|---|
Country | Netherlands |
City | Enschede |
Period | 9/11/09 → 10/11/09 |
Keywords
- METIS-264622
- IR-69549
- nearest neighbour classification
- BSS-Biomechatronics and rehabilitation technology
- EWI-17227
- multi-electrode sEMG
- Myoelectric prosthesis