A Hybrid Neuro-fuzzy Approach for Spinal Force Evaluation in Manual Materials Handling Tasks
Evaluation of the spinal forces from kinematics data is very complicated because it involves the handling of relationship between kinematic variables and electromyography (EMG) responses, as well as the relationship between EMG responses and the forces. A recurrent fuzzy neural network (RFNN) model is proposed to establish the kinematics-EMG-force relationship and model the dynamics of muscular activities. The EMG signals are used as an intermediate output and are fed back to the input layer. Since the EMG signal is a direct reflection of muscular activities, the feedback of this model has a physical meaning. It expresses the dynamics of muscular activities in a straightforward way and takes advantage from the recurrent property. The trained model can then have the forces predicted directly from kinematic variables while bypassing the procedure of measuring EMG signals and avoiding the use of biomechanics model. A learning algorithm is derived for the RFNN.
Unable to display preview. Download preview PDF.
- 6.Hussein, S.E., Granat, M.H.: Intention detection using a neuro-fuzzy EMG classifier. Engineering in Medicine and Biology Magazine, IEEE 21(6), 123–129 (November-December)Google Scholar
- 8.Hou, Y., Zurada, J.M., Karwowski, W.: Prediction of EMG Signals of Trunk Muscles in Manual Lifting Using a Neural Network Model. In: Proc. of the Int. Joint Conf. on Neural Networks, July 25-29, pp. 1935–1940 (2004)Google Scholar
- 9.Hou, Y., Zurada, J.M., Karwowski, W.: Prediction of Dynamic Forces on Lumbar Joint Using a Recurrent Neural Network Model. In: Proc. of the 2004 Int. Conf. on Machine Learning and Applications (ICMLA 2004), December 16-18, pp. 360–365 (2004)Google Scholar
- 10.Wu, S., Er, M.J.: Dynamic fuzzy neural networks-a novel approach to function approximation. IEEE Trans. on Systems, Man and Cybernetics B 30, 358–364 (2000)Google Scholar
- 17.Lin, F.J., Wai, R.J., Hong, C.M.: Hybrid supervisory control using recurrent fuzzy neural network for tracking periodic inputs. IEEE Trans. on Neural Networks 12(1), 102–115 (2001)Google Scholar
- 20.Hou, Y., Zurada, J.M., Karwowski, W.: Identification of Input Variables using Fuzzy Average with Fuzzy Cluster Distribution. Submitted to IEEE Trans. on Fuzzy SystemsGoogle Scholar