Probabilistic inference-based classification applied to myoelectric signal decomposition

A probabilistic inference-based classification (IBC) technique for classifying motor unit action potentials (MUAPs) is presented. This technique discovers statistically significant relationships in the data and uses them to generate classification rules. The technique was applied to the classification of MUAPs extracted from simulated myoelectric signals. Its performance was compared to that of classical template-based classification algorithms (TBC). It was found that the IBC-based technique performed significantly better than the TBC algorithms. As the size of the training set was reduced or as increasing numbers of random classification errors were introduced into the training data, the performance of the IBC and TBC techniques declined similarly. IBC performance remained superior until very small training sets or training sets with large numbers of errors were used. Because the technique can utilize nominal data it has the potential to use declarative problem domain knowledge, which conceivably could improve its performance.<<ETX>>