Probabilistic inference-based classification applied to myoelectric signal decomposition.

A new probabilistic inference based technique (IBC) for the classification of motor unit action potentials (MUAP's) is presented. This new technique discovers statistically significant relationships in the data and uses these relationships to generate classification rules. The technique was applied to the classification of MUAP's extracted from simulated myoelectric signals. Its performance was compared to that of classical template matching algorithms (TBC) applied to the same data. Using 32 time samples as features to represent the MUAP's it was found that the IBC based technique performed significantly better (p less than 0.005) than the TBC algorithms (83.0 +/- 2.6% versus 78.1 +/- 2.8% peak correct classification performance). 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 (less than 30 MUAP's per motor unit) or training sets with large numbers of errors (greater than 50%) were used. Because the probabilistic inference technique can utilize nominal data it has the potential to use declarative problem domain knowledge which conceivably could improve its performance.