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. © 2014 IEEE.
Multi-source adaptive learning for fast control of prosthetics hand / Patricia, Novi; Tommasi, Tatiana; Caputo, Barbara. - (2014), pp. 2769-2774. (Intervento presentato al convegno 22nd International Conference on Pattern Recognition, ICPR 2014 tenutosi a Stockholm; Sweden nel 2014) [10.1109/ICPR.2014.477].
Multi-source adaptive learning for fast control of prosthetics hand
Patricia, Novi;Tommasi, Tatiana
;Caputo, Barbara
2014
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. © 2014 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
