TY - GEN
T1 - Towards smart prosthetic hand
T2 - 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
AU - Kumar, Parmod
AU - Sebastian, Anish
AU - Potluri, Chandrasekhar
AU - Urfer, Alex
AU - Naidu, D. Subbaram
AU - Schoen, Marco P.
PY - 2010/12/1
Y1 - 2010/12/1
N2 - Skeletal muscle force can be estimated using surface electromyographic (sEMG) signals. Usually, the surface location for the sensors is near the respective muscle motor unit points. Skeletal muscles generate a spatial EMG signal, which causes cross talk between different sEMG signal sensors. In this study, an array of three sEMG sensors is used to capture the information of muscle dynamics in terms of sEMG signals. The recorded sEMG signals are filtered utilizing optimized nonlinear Half-Gaussian Bayesian filters parameters, and the muscle force signal using a Chebyshev type-II filter. The filter optimization is accomplished using Genetic Algorithms. Three discrete time state-space muscle fatigue models are obtained using system identification and modal transformation for three sets of sensors for single motor unit. The outputs of these three muscle fatigue models are fused with a probabilistic Kullback Information Criterion (KIC) for model selection. The final fused output is estimated with an adaptive probability of KIC, which provides improved force estimates.
AB - Skeletal muscle force can be estimated using surface electromyographic (sEMG) signals. Usually, the surface location for the sensors is near the respective muscle motor unit points. Skeletal muscles generate a spatial EMG signal, which causes cross talk between different sEMG signal sensors. In this study, an array of three sEMG sensors is used to capture the information of muscle dynamics in terms of sEMG signals. The recorded sEMG signals are filtered utilizing optimized nonlinear Half-Gaussian Bayesian filters parameters, and the muscle force signal using a Chebyshev type-II filter. The filter optimization is accomplished using Genetic Algorithms. Three discrete time state-space muscle fatigue models are obtained using system identification and modal transformation for three sets of sensors for single motor unit. The outputs of these three muscle fatigue models are fused with a probabilistic Kullback Information Criterion (KIC) for model selection. The final fused output is estimated with an adaptive probability of KIC, which provides improved force estimates.
UR - http://www.scopus.com/inward/record.url?scp=78650848350&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650848350&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2010.5626388
DO - 10.1109/IEMBS.2010.5626388
M3 - Conference contribution
C2 - 21095927
AN - SCOPUS:78650848350
SN - 9781424441235
T3 - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
SP - 1316
EP - 1319
BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Y2 - 31 August 2010 through 4 September 2010
ER -