TY - JOUR
T1 - Continuous detection and decoding of dexterous finger flexions with implantable myoelectric sensors
AU - Baker, Justin J.
AU - Scheme, Erik
AU - Englehart, Kevin
AU - Hutchinson, Douglas T.
AU - Greger, Bradley
N1 - Funding Information:
Manuscript received October 05, 2009; revised December 01, 2009; accepted January 25, 2010. First published April 08, 2010; current version published August 11, 2010. This work was supported in part by DARPA BAA05-26 Revolutionizing Prosthetics. J. J. Baker and B. Greger are with the Bioengineering Laboratory, University of Utah, Salt Lake City, UT 84602 USA. E. Scheme is with the Institute of Biomedical Engineering, University of New Brunswick, Fredericton, NB, E3B 5A3 Canada. K. Englehart is with the Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB, E3B 5A3 Canada. D. T. Hutchinson is with the Department of Orthopaedics, University of Utah, Salt Lake City, UT 84108 USA. Color versions of one ore more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TNSRE.2010.2047590
PY - 2010/8
Y1 - 2010/8
N2 - A rhesus monkey was trained to perform individuated and combined finger flexions of the thumb, index, and middle finger. Nine implantable myoelectric sensors (IMES) were then surgically implanted into the finger muscles of the monkey's forearm, without any adverse effects over two years postimplantation. Using an inductive link, EMG was wirelessly recorded from the IMES as the monkey performed a finger flexion task. The EMG from the different IMES implants showed very little cross correlation. An offline parallel linear discriminant analysis (LDA) based algorithm was used to decode finger activity based on features extracted from continuously presented frames of recorded EMG. The offline parallel LDA was run on intraday sessions as well as on sessions where the algorithm was trained on one day and tested on following days. The performance of the algorithm was evaluated continuously by comparing classification output by the algorithm to the current state of the finger switches. The algorithm detected and classified seven different finger movements, including individual and combined finger flexions, and a no-movement state (chance performance = 12.5%). When the algorithm was trained and tested on data collected the same day, the average performance was 43.8 ± 3.6 %n=10. When the training-testing separation period was five months, the average performance of the algorithm was 46.5 ± 3.4 %n=8. These results demonstrated that using EMG recorded and wirelessly transmitted by IMES offers a promising approach for providing intuitive, dexterous control of artificial limbs where human patients have sufficient, functional residual muscle following amputation.
AB - A rhesus monkey was trained to perform individuated and combined finger flexions of the thumb, index, and middle finger. Nine implantable myoelectric sensors (IMES) were then surgically implanted into the finger muscles of the monkey's forearm, without any adverse effects over two years postimplantation. Using an inductive link, EMG was wirelessly recorded from the IMES as the monkey performed a finger flexion task. The EMG from the different IMES implants showed very little cross correlation. An offline parallel linear discriminant analysis (LDA) based algorithm was used to decode finger activity based on features extracted from continuously presented frames of recorded EMG. The offline parallel LDA was run on intraday sessions as well as on sessions where the algorithm was trained on one day and tested on following days. The performance of the algorithm was evaluated continuously by comparing classification output by the algorithm to the current state of the finger switches. The algorithm detected and classified seven different finger movements, including individual and combined finger flexions, and a no-movement state (chance performance = 12.5%). When the algorithm was trained and tested on data collected the same day, the average performance was 43.8 ± 3.6 %n=10. When the training-testing separation period was five months, the average performance of the algorithm was 46.5 ± 3.4 %n=8. These results demonstrated that using EMG recorded and wirelessly transmitted by IMES offers a promising approach for providing intuitive, dexterous control of artificial limbs where human patients have sufficient, functional residual muscle following amputation.
KW - Decode
KW - electromyography
KW - fingers
KW - parallel algorithms
UR - http://www.scopus.com/inward/record.url?scp=77955641917&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955641917&partnerID=8YFLogxK
U2 - 10.1109/TNSRE.2010.2047590
DO - 10.1109/TNSRE.2010.2047590
M3 - Article
C2 - 20378481
AN - SCOPUS:77955641917
SN - 1534-4320
VL - 18
SP - 424
EP - 432
JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering
JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering
IS - 4
M1 - 5445014
ER -