Abstract | ||
---|---|---|
We present a benchmark of several existing multi-source adaptive methods on the largest publicly available database of surface electromyography signals for polyarticulated self-powered hand prostheses. By exploiting the information collected over numerous subjects, these methods allow to reduce significantly the training time needed by any new prosthesis user. Our findings provide the bio robotics community with a deeper understanding of adaptive learning solutions for user-machine control and pave the way for further improvements in hand-prosthetics. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICPR.2014.477 | Pattern Recognition |
Keywords | Field | DocType |
electromyography,learning (artificial intelligence),medical signal processing,prosthetics,biorobotics community,fast prosthetics hand control,multisource adaptive learning,polyarticulated self-powered hand prostheses,surface electromyography signals,user-machine control | Computer science,Biorobotics,Artificial intelligence,Adaptive learning,Multi-source,Machine learning | Conference |
ISSN | Citations | PageRank |
1051-4651 | 6 | 0.46 |
References | Authors | |
13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Novi Patricia | 1 | 6 | 0.46 |
Tatiana Tommasi | 2 | 502 | 29.31 |
Barbara Caputo | 3 | 3298 | 201.26 |