An automatic system for clustering and visualization of motor unit action potentials based on generative topographic mapping

An important stage in studies seeking to explain the behaviour of the neuromuscular system is the visualization and extraction of motor unit action potentials (MUAPs) from electromyographic (EMG) signals. This paper presents a system based on the generative topographic mapping (GTM), a novel probabilistic model for data analysis, for detection, clustering and visualization of MUAPs. Results obtained from the analysis of synthetic and experimental EMG signals showed that this system could successfully extract MUAPs from EMGs.