This work represents an ongoing investigation of dexterous and natural cont
rol of powered upper limbs using the myoelectric signal. When approached as
a pattern recognition problem, the success of a myoelectric control scheme
depends largely on the classification accuracy. A novel approach is descri
bed that demonstrates greater accuracy than in previous work. Fundamental t
o the success of this method is the use of a wavelet-based feature set, red
uced in dimension by principal components analysis. Further, it is shown th
at four channels of myoelectric data greatly improve the classification acc
uracy, as compared to one or two channels. It is demonstrated that exceptio
nally accurate performance is possible using the steady-state myoelectric s
ignal. Exploiting these successes, a robust online classifier is constructe
d, which produces class decisions on a continuous stream of data. Although
in its preliminary stages of development, this scheme promises a more natur
al and efficient means of myoelectric control than one based on discrete, t
ransient bursts of activity.