پيش بيني نيروي انقباض ايزومتريك در عضله فلج تحريك شده با استفاده از شبكه هاي عصبي خودسازنده

In this work, we develop a method for estimating the force generated by electrically stimulated muscle during isometric contraction based upon measurements of the Evoked EMG (EEMG) and stimulation by using artificial neural networks. For this purpose, we employ a radial basis function (RBF) neural network with gradient descent leaning algorithm. In the classical approach to RBF network implementation, the number of hidden units is predetermined. It, usually, results in large or small network. Too small networks are unable to adequately learn the problem well while overly large networks tend to overfit the training data. To overcome this drawback, we employ a learning algorithm for incremental construction of neural network architecture. The algorithm starts with a small network and dynamically grows the network with adding neurons as needed until a satisfactory solution is found. The results show that the self-constructing neural network method can improve the predictability of muscle force with a suitable number of hidden units compared to the RBF and back-propagation neural network. Three types of models are considered here: (1) EEMG-to-torque model relating the EEMG to measured torque; (2) stimulation-to-torque model relating the stimulation to the muscle torque; and (3) stimulation & EEMG-to-torque model. In the third model, the stimulation signal as well as measured EEMG constitutes the input of the muscle model. The results of this work indicate that the use of the measured EEMG as the input to a predictive model of muscle torque generation is superior to the use of the electrical stimulation signal as the model input. This is because the measured EEMG captures all of the neural excitation, whereas stimulation-to-torque models only reflect that portion of the neural excitation that results directly from stimulation.