Abstract
Muscle modelling is an important component of body segmental motion analysis. Although many studies had focused on static conditions the relationship between electromyographic (EMG) signals and joint torque under voluntary dynamic situations has not been well investigated. The aim of this study was to investigate the performance of a recurrent artificial neural network (RANN) under voluntary dynamic situations for torque estimation of the elbow complex. EMG signals together with kinematic data, which included angle and angular velocity, were used as the inputs to estimate the expected torque during movement. Moreover, the roles of angle and angular velocity in the accuracy of prediction were investigated, and two models were compared. One model used EMG and joint kinematic inputs and the other model used only EMG inputs without kinematic data. Six healthy subjects were recruited, and two average angular velocities (60o s−1 and 90o s−1) with three different loads (0 kg, 1 kg, 2 kg) in the hand position were selected to train and test the RANN between 90o elbow flexion and full elbow extension (0o). After training, the root mean squared error (RMSE) between expected torque and predicted torque of the model, with EMG and joint kinematic inputs in the training data set and the test data set were 0.17±0.03 Nm and 0.35±0.06 Nm, respectively. The RMSE values between expected torque and predicted torque of the model, with only EMG inputs in the training data set and the test set, were 0.57±0.07 Nm and 0.73±0.11 Nm, respectively. The results showed that EMG signals together with kinematic data gave significantly better performance in the joint torque prediction; joint angle and angular velocity provided important information in the estimation of joint torque in voluntary dynamic movement.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Au, A. T. C., andKirsch R. F. (2000): ‘EMG-based prediction of shoulder and elbow kinematics in able-bodied and spinal cord injured individuals’,IEEE Trans. Rehab. Eng.,8, pp. 471–480
Brown, M., andHarris, C. (1994): ‘Neurofuzzy adaptive modelling and control’, (Prentice Hall, 1994)
Cheron, G., Draye, J. P., Bourgeios, M., andLibert, G. (1996): ‘A dynamic neural network identification of electromyography and arm trajectory relationship during complex movements’,IEEE Trans. Biomed. Eng.,43, pp. 552–558
Cram, J. R., Kasman, G. S., andHoltz, J. (1998): ‘Introduction to surface electromyography’ (Aspen Publishers, Gaithersburg, 1998)
Dipietro, L., Sabatini, A. M., andDario, P. (2003): ‘Artificial neural network model of the mapping between electromyographic activation and trajectory patterns in free-arm movements’,Med. Biol. Eng. Comput.,41, pp. 125–132
Feng, J., Mak, A. F. T., andKoo, T. K. K. (1999): ‘A surface EMG driven musculoskeletal model of the elbow flexion-extension movement in normal subjects and in subjects with spasticity’,J. Musculoskel. Res.,3, pp. 109–123
Gregor, R. J., Komi, P. V., Browning, R. C., andJarvinen, M. (1991): ‘A comparison of the triceps surae and residual muscle moments at the ankle during cycling’,J. Biomech.,24, pp. 287–297
Gurbuz, H., Kivrak, E., Soyupak, S., andYerli, S. V. (2003): ‘Predicting dominant phytoplankton quantities in a reservoir by using neural networks’,Hydrobiologia,504, pp. 133–141
Hill, A. V. (1938): ‘The heat of shortening and the dynamic constants of muscle’,Proc. R. Soc. Lond. Biol.,126, pp. 136–195
Hirose, Y., Yamashita, K., andHijiya, S. (1991): ‘Back-propagation algorithm which varies the number of hidden units’,Neural Netw.,4, pp. 61–66.
Koike, Y., andKawato, M. (1995): ‘Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model’,Biol. Cybernet.,73, pp. 291–300
Liu, M. M., Herzog, W., andSavelberg, H. C. M. (1999): ‘Dynamic muscle force predictions from EMG: an artificial neural network approach’,J. Electromyogr. Kinesiol.,9, pp. 391–400
Lloyd, D. G., andBesier, T. F. (2003): ‘An EMG-driven musculoskeletal model to estimate muscle forces and knee joint momentsin vivo’,J. Biomech.,36, pp. 765–776
Luh, J. J., Chang, G. C., Cheng C. K., Lai, J. S., andKuo, E. S. (1999): ‘Isokinetic elbow joint torques estimation from surface EMG and joint kinematic data: using an artificial neural network model’,J. Electromyogr. Kinesiol.,9, pp. 173–183
Manal, K., Gonzalez, R. V., Lloyd, D. G., andBuchanan, T. S. (2002): ‘A real-time EMG-driven virtual arm’,Comput. Biol. Med.,32, pp. 25–36
Misener, D. L. andMorin, E. L. (1995): ‘An EMG to force model for the human elbow derived from surface EMG’.IEEE-EMBC & CMBEC, pp. 1205–1206
Riener, R., andStraube, A. (1997): ‘Inverse dynamics as a tool for motion analysis: arm tracking movements in cerebellar patients’,J. Neurosci. Meth.,72, pp. 87–96
Rosen, J., Fuchs, M. B., andArcan, M. (1999): ‘Performances of hill-type and neural network muscle models towards a myosignal based exoskeleton’,Comput. Biomed. Res.,32, pp. 415–439
Tong, K. Y. (1997): ‘Artificial neural network control of FES gait using virtual kinematic sensors’, PhD thesis, University of Strathclyde, UK
Uchiyama, T., Bessho, T., andAkazawa, K. (1998): ‘Static torqueangle relation of human elbow joint estimated with artificial neural network technique’,J. Biomech.,31, pp. 545–554
Wang, L., andBuchanan, T. S. (2002): ‘Prediction of joint moments using a neural network model of muscle activations from EMG signals’,IEEE Trans. Neur. Syst. Rehab. Eng.,10, pp. 30–37
Winter, D. A. (1990): ‘Biomechanics and motor control of human movement’ (Wiley, New York, 1990)
Winters, J. M., andStark, L. (1988): ‘Estimated mechanical properties of synergistic muscles involved in movements of a variety of human joint’,J. Biomech.,21, pp. 1027–1041
Winters, J. M. (1990): ‘Hill-based muscle models: a systems engineering perspective’, inWinters, J. M., andWoo, S. L. Y. (Eds): ‘Multiple muscle systems: Biomechanics and movement organization’ (Springer-Verlag, Berlin, 1990), pp. 69–93
Zajac, F. E. (1989): ‘Muscles and tendon: properties, models, scaling, and application to biomechanics and motor control’,Crit. Rev. Biomed. Eng.,17, pp. 359–411
Zajac, F. E., andWinter, J. M. (1990): ‘Modeling musculo-skeletal movement system: joint and body segmental dynamics, musculoskeletal actuation, and neuromuscular control’, inWinters, J. M., andWoo, S. L. Y. (Eds) ‘Multique muscle systems’ (Springer-Verlag, Berlin, 1990), pp. 121–148
Zhang, Y. T., Herzog, W., andLiu, M.M. (1997): ‘Adaptive demodulation of muscular force from myoelectric signals obtained during locomotion’.IEEE-EMBC & CMBEC, pp. 1401–1402
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Song, R., Tong, K.Y. Using recurrent artificial neural network model to estimate voluntary elbow torque in dynamic situations. Med. Biol. Eng. Comput. 43, 473–480 (2005). https://doi.org/10.1007/BF02344728
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02344728