Title :
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
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;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
DOI :
10.1109/TIM.2003.816841
