Title :
Rule-Based Learning for More Accurate ECG Analysis
Author :
Birman, Kenneth P.
Author_Institution :
Computer Science Division, Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA 94720; 100 Wellington Avenue, New Rochelle, NY 10804.
fDate :
7/1/1982 12:00:00 AM
Abstract :
Long-term electrocardiograms exhibit a small number of QRS morphologies (waveform shapes) whose analysis can reveal cardiac abnormalities. We considered the problem of accurately identifying instances of each in 24-h ECG recordings. A new learning algorithm was developed. Each QRS morphology is represented as a tree of rule activations, which associate attribute measurements with a rule. Each rule has a syntactic pattern together with a semantic procedure which manages and applies the knowledge stored in the activation. A single rule may be activated several times to learn different waveform segments. Delineation refinement improves each hypothesized signal interpretation. A simple conflict resolution mechanism resolves conflicting interpretations into a single unambiguous one. Comparison of the system with an existing program confirmed the promise of the new approach.
Keywords :
Electrocardiography; Heart; Knowledge management; Knowledge representation; Morphology; Pattern recognition; Rhythm; Shape; Signal processing algorithms; Signal resolution; Electrocardiogram (ECG) analysis; interactive signal processing; knowledge representation; learning; pattern recognition languages (SEEK); rule-based learning; syntax directed inference;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1982.4767268