A novel approach to the control of a multifunction prosthesis based on the classification of
myoelectric patterns is described. It is shown that the myoelectric signal exhibits a
deterministic structure during the initial phase of a muscle contraction. Features are
extracted from several time segments of the myoelectric signal to preserve pattern structure.
These features are then classified using an artificial neural network. The control signals are
derived from natural contraction patterns which can be produced reliably with little subject …

One of the limitations of current multifunction myoelectric control systems is the amount of
myoelectric signal data required to classify with a reasonable accuracy the signals to be
used as a control input. The amount of data required introduces a time delay in the
myoelectric control systems which hinders the development of a continuous type of control.
A new strategy is proposed to handle this limitation by employing an array of surface
electrodes and correlation feature vector. The aim is to develop a new strategy which can …