Identification of the human arm kinetics using dynamic recurrent neural networks.
Jean-Philippe Draye, Guy Chéron, Marc Bourgeois, Davor Pavisic, G. Libert · 1995
. Artificial neural networks offer an exciting alternative for modeling and identifying complex non-linear systems. This paper investigates the identification of discrete-time non-linear systems using dynamic recurrent neural networks. We use this kind of networks to efficiently identify the complex temporal relationship between the patterns of muscle activation represented by the electromyography signal (EMG) and their mechanical actions in three-dimensional space. The results show that dynamic neural networks provide a successful platform for biomechanical modeling and simulation including complex temporal relationships. 1. Introduction The cause-and-effect sequence of events that takes place for a human movement to occur is complex : after a registration of the movement command in the central nervous system, there is a transmission of the movement signals to the peripherical nervous system; these signals induce the contraction of the muscles that develop tension (with con...