“…Most of the clustering techniques developed for EMG decomposition are based on adaptations of general clustering algorithms such as the nearest-neighbor [1], [26], [53], [115], single linkage [54], [55], [91], [93], [94], [116], [117], K-means [1], [7], [26], [68], [74], fuzzy c-means [66], [67], [118], minimal spanning tree [54][55][56], [59], [65], [69], [119], [120], leader-based clustering [6], [25], and self-organizing neural nets algorithm [58]. In many of these algorithms MU firing pattern information is used passively or actively along with MUP shape information to assign an individual MUP to the correct train.…”