On-line heart beat recognition using Hermite polynomials and neuro-fuzzy network

Author

Linh, Tran Hoai ; Osowski, Stanislaw ; Stodolski, Maciej

Author_Institution

Inst. of the Theor. of Electr. Eng. & Electr. Meas., Warsaw Univ. of Technol., Poland

Volume

52

Issue

4

fYear

2003

Firstpage

1224

Lastpage

1231

Abstract

This paper presents a neuro-fuzzy approach to the recognition and classification of heart rhythms on the basis of ECG waveforms. The important part in recognition fulfills the Hermite characterization of the QRS complexes. The Hermite coefficients serve as the features of the process. These features are applied to a fuzzy neural network for recognition. The results of numerical experiments have confirmed very good performance of such a solution.

Keywords

electrocardiography; fuzzy neural nets; medical signal processing; patient diagnosis; pattern classification; ECG pattern classification; ECG pattern recognition; ECG waveforms; Hermite expansion coefficients; Hermite function expansion; Hermite polynomials; QRS complex Hermite characterization; Takagi-Sugeno-Kang network; arrhythmia recognition; electrocardiography; fuzzy neural network; heart rhythms; neuro-fuzzy TSK network; neuro-fuzzy network; on-line heart beat recognition; Character recognition; Electric variables measurement; Electrocardiography; Fuzzy neural networks; Heart beat; Heart rate variability; Helium; Polynomials; Rhythm; Training data;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/TIM.2003.816841

Filename

1232372