ADAPTIVE MOTOR UNIT ACTION-POTENTIAL CLUSTERING USING SHAPE AND TEMPORAL INFORMATION

An adaptive algorithm is described that groups motor unit action poten tials (MUAPs), detected in a composite EMG signal during signal decomp osition, and creates partial motor unit action potential trains (MUAPT s). Data-driven MUAP shape and motor unit firing-pattern based criteri a are used to form the clusters. An algorithm for estimating MUAPT tem poral parameters, which provides accurate estimates even for partially defined trains, is used to obtain firing-pattern information. No a pr iori knowledge is required regarding the number of clusters or the dis tribution of their template shapes. The clustering algorithm when appl ied to real concentric-needle detected MUAP data provides accurate and useful clustering results. Compared to a classical leader-based algor ithm, it provides more robust performance, is better able to estimate the true number of motor units represented in a set of detected MUAPs, and obtains more complete and accurate MUAPTs.