학술논문
Multicategory classification of body surface potential maps
Document Type
Periodical
Author
Source
IEEE Transactions on Biomedical Engineering IEEE Trans. Biomed. Eng. Biomedical Engineering, IEEE Transactions on. 37(10):945-955 Oct, 1990
Subject
Language
ISSN
0018-9294
1558-2531
1558-2531
Abstract
A statistical classification method is suggested for body surface potential maps (BSPM). The initial data reduction utilizes the Fourier expansion and time integration, resulting in physiologically oriented features. Based on Fischer's criterion, optimal discriminant vectors are used to map the features to an optimal subdomain. Experimental criteria determine the dimensionality of the subdomain and the number of features to be mapped into it. Classification is performed in two steps. In the first, a k-nearest neighbor (k-NN) rule is used for every two-category problem, the results of which are then fed into a voting rule for final classification. The method is tested with 123 patients divided into four categories: normal (NR), ischemia (IS), myocardial infarction (MI), and left bundle branch block (LB) patients. The success is between 88% (IS) and 100% (for LB) for QRS segment integration. Departure maps were used to explain the misclassified patterns.ETX