Myoelectrically controlled prostheses use pattern recognition systems to classify input motions. Typically, these systems are initially trained offline using a set of training data. Changing conditions cause an increase in signal variation, leading to higher error rates. For better adaptability, a continuously trained classifier was developed. Data with valid class decisions are used to retrain the classifier with the class decisions used as classification targets. In this implementation the classifier validates decisions by using a retraining buffer to locate consecutive, identical majority vote decisions. Retraining is performed by incorporating new valid feature vectors, selected from the retraining buffer, into the training set, while discarding older vectors. Using the continuously trained classifier, an average improvement of 2.57% was seen over the non-continuously trained classifier.

Additional Metadata
Keywords Linear discriminant analysis, Myoelectric signals, Pattern recognition, Prosthesis
Conference Conference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004
Citation
Plumb, A.W. (A. W.), Chan, A, & Goge, A.R. (A. R.). (2004). Continuous classifier training for myoelectrically controlled prostheses. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (pp. 474–477).