Supervised classification of motor unit action potentials based on estimates of classification certainty

The classification of motor unit action potentials extracted from a myoelectric (ME) signal is a difficult task due to the lack of a priori information regarding the number of classes and the class statistics. Classification can be performed with great accuracy by humans due to inherent pattern anal...

Full description

Saved in:
Bibliographic Details
Main Authors: Paoli, G.M., Stashuk, D.W.
Format: Conference Proceeding
Language:English
Subjects:
Decision making
Design engineering
Euclidean distance
Humans
Information resources
Pattern analysis
Probability
Shape
Signal generators
Signal resolution
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The classification of motor unit action potentials extracted from a myoelectric (ME) signal is a difficult task due to the lack of a priori information regarding the number of classes and the class statistics. Classification can be performed with great accuracy by humans due to inherent pattern analysis and decision-making abilities. In trying to match the performance of the human operator, a method was developed to combine various sources of information into a certainty function which mimics the degree of certainty a human might have about a classification, given the same information. This method is described and preliminary comparative results provided.
DOI:10.1109/IEMBS.1993.979099