A neural network weight pattern study with ECG pattern recognition

Author

Xue, Qiuzhen ; Hu, Yuhen ; Tompkins, Willis J.

Author_Institution

Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA

fYear

1989

fDate

9-12 Nov 1989

Firstpage

2023

Abstract

Singular-value decomposition (SVD) is used to analyze the weight pattern of a back-propagation (BP) model for efficient classification of ECG waveforms. It is found that the rank of a matrix formed by all the weights, which can be determined by SVD of that matrix, is a good indicator of the number of hidden nets needed. The SVD is also used to analyze the relationship between the weight patterns and the learned features of the input patterns

Keywords

computerised pattern recognition; electrocardiography; medical diagnostic computing; neural nets; waveform analysis; ECG pattern recognition; ECG waveforms; back propagation model; efficient classification; learned features; neural network weight pattern study; singular value decomposition; Biological system modeling; Electrocardiography; Engineering in medicine and biology; Matrix decomposition; Neural networks; Pattern analysis; Pattern recognition; Singular value decomposition; Societies; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in

Conference_Location

Seattle, WA

Type

conf

DOI

10.1109/IEMBS.1989.96576

Filename

96576