Title :
Fast neural system identification: application to rehabilitation engineering
Author :
Madan, S. ; Thrasher, A. ; Andrews, B.J.
Abstract :
To develop a powered hybrid FES (functional electrical stimulation) orthosis for paraplegics, fast system identification techniques play a crucial role to obtain information about the neuromuscular system. However, the underlying systems have nonlinear and coupled dynamics with uncertainties in practice. Artificial neural networks provide such adaptive nonlinear models and can be well extended to system identification or prediction problems. In this research, fast and robust online identification using a multi-layer recurrent neural network is tackled in two steps: a multi-layer network architecture through a supervisory-signal and error recurrent neural network (SERNN); and robust training through a modified recursive least-squares algorithm, having a dynamic forgetting factor and an optimal teaching signal for the hidden layer
Keywords :
biomedical engineering; handicapped aids; identification; learning (artificial intelligence); least squares approximations; medical computing; multilayer perceptrons; neural net architecture; orthotics; recurrent neural nets; adaptive nonlinear models; coupled dynamics; dynamic forgetting factor; functional electrical stimulation; hidden layer; multilayer recurrent neural network; neural network architecture; neural system identification; neuromuscular system; nonlinear dynamics; online identification; optimal teaching signal; orthosis; paraplegics; prediction problems; recursive least-squares algorithm; rehabilitation engineering; robust training; supervisory-signal and error recurrent neural network; uncertainties; Adaptive systems; Artificial neural networks; Couplings; Neuromuscular stimulation; Nonlinear dynamical systems; Predictive models; Recurrent neural networks; Robustness; System identification; Uncertainty;
Conference_Titel :
Communications, Computers and Signal Processing, 1997. 10 Years PACRIM 1987-1997 - Networking the Pacific Rim. 1997 IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-3905-3
DOI :
10.1109/PACRIM.1997.620320
