Title :
Joint position and velocity derived from muscle spindle output: a neural network approach
Author :
Ewert, Dan ; Akers, Thomas
Author_Institution :
Dept. of Physiol., North Dakota Univ. Sch. of Med., Grand Forks, ND, USA
Abstract :
The results obtained when a mathematical model of a two-muscle hinge joint is combined with a muscle spindle model are presented. Passive joint motion is imposed on the joint model, causing muscle stretch. The stretch is used to determine the muscle spindle firing rates, which are subsequently used as training data for a neural network. A neural net has been trained to recognize joint position and velocity from muscle spindle output for a variety of conditions
Keywords :
biomechanics; mechanoception; muscle; neural nets; physiological models; 2-muscle hinge joint; joint position; joint velocity; mathematical model; muscle spindle firing rate; muscle spindle output; muscle stretch; neural network approach; passive joint motion; training data; Back; Joints; Mathematical model; Muscles; Neodymium; Neural networks; Neurons; Physiology; Read only memory; Training data;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.95937
