On the separation of semiperiodic superimposed point processes: application to electromyographic signals.

A method for the separation of semiperiodic (Gaussian probability distribution of intervals with moderate coefficient of variation) superimposed point processes, to be implemented on a digital computer is described. The efficiency of the filter used for the extraction of the underlying event sequences from the pooled array has been investigated by simulation. Approximately 80 percent of the events belonging to the underlying sequence to be extracted were recovered (with the addition of "impurity events"), still preserving the mean rate and coefficient of variation of the original indicidual sequence concerned. The program was used on an example of an actual electromyographic recording (comprised of a number of motor units discharging simultaneously), resolving the number of motor units involved, their mean rates, and the coefficient of variation of the individual action potential sequences.