EMG-Based Muscle Torque Estimation for FES Control System Design
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
This study was designed to investigate the feasibility to utilize the electromyogram (EMG) for estimating the muscle torque. The muscle torque estimation plays an important role in functional electrical stimulation because electrical stimulation causes muscles to fatigue much faster than voluntary contraction, and the stimulation intensity should then be modified to keep the muscle torque within the desired range. We employed the neural network method which was trained using the major EMG parameters and the corresponding knee extensor torque measured and extracted during isometric contractions. The experimental results suggested that (1) our neural network algorithm and protocol was feasible to be adopted in a real-time feedback control of the stimulation intensity, (2) the training data needed to cover the entire range of the measured value, (3) different amplitudes and frequencies made little difference to the estimation quality, and (4) a single input to the neural network led to a better estimation rather than a combination of two or three. Since this study was done under a limited contraction condition, the results need more experiments under many different contraction conditions, such as during walking, for justification.
Abstract
This study was designed to investigate the feasibility to utilize the electromyogram (EMG) for estimating the muscle torque. The muscle torque estimation plays an important role in functional electrical stimulation because electrical stimulation causes muscles to fatigue much faster than voluntary contraction, and the stimulation intensity should then be modified to keep the muscle torque within the desired range. We employed the neural network method which was trained using the major EMG parameters and the corresponding knee extensor torque measured and extracted during isometric contractions. The experimental results suggested that (1) our neural network algorithm and protocol was feasible to be adopted in a real-time feedback control of the stimulation intensity, (2) the training data needed to cover the entire range of the measured value, (3) different amplitudes and frequencies made little difference to the estimation quality, and (4) a single input to the neural network led to a better estimation rather than a combination of two or three. Since this study was done under a limited contraction condition, the results need more experiments under many different contraction conditions, such as during walking, for justification.
참고문헌 (10)
- A. Erfanian, "Using evoked EMG as a synthetic force sensor of isometric electrically stim- ulated muscle", 45(2), pp.18~202 (1998)
- D. Tepavac, "Detection and prediction of FES-induced fatigue", 7(1), pp.39~50 (1997)
- L. M. Kent, "Modeling of muscle EMG to torque by the neural network model of backpropagation in Proc. Annual International Conference of the IE Enginering in Medicine and Biology Society", 12, pp.1477~1478 (1990)
- J. Winslow, "Fatigue comp- ensation during FES using surface EMG", 13, pp.55~568 (2003)
- M. M. Liu, "Dynamic muscle force predictions from EMG : an artificial neural network aproach", 9, pp.391~400
- T. Song, "Efects of pulse waveforms and muscle lengths on muscle force and fatigue resistance", pp.349~351 (2005), in Proc. 10th Annual Conference of the International Functional Electrical Stimulation Society
- S. H. Hwang, "Relationship betwen some major EMG parameters and muscle torque", pp.193~ (2004), in Proc. 31 thKorea Society of Medical & Biological Enginering
- H. Abdi, "Neural Networks", pp.61~87, SAGE publications
- J. Luh, "Isokinetic elbow torques estimation from surface EMG and joint kinematic data: using an artificial neural network model", 9, pp.173~183 (1999)
- H. H.C.M. Savelberg, "Prediction of dynamic tendon forces from electromyographic signals: an artificial neural network approach", 78, pp.65~74 (1997)