Measurement 12-lead ECG character points using line segment clustering technique

Author

Shey, Jenn Taur ; Lin, Kan-Ping ; Chang, Walter H.

Author_Institution

Dept. of Biomed. Eng., Chung Yuan Christian Univ., Chung Li, Taiwan

fYear

1998

fDate

29 Oct-1 Nov 1998

Firstpage

223

Abstract

A new technique for ECG character points measurement is presented. The linear approximation distance thresholding (LADT) and line segment clustering (LSC) technique are combined to process the ECG signal, and recognize the important points of one beat ECG signal. In this study, several character points, such as R peak and T peak are recognized by the technique. The results of LSC technique are compared to manual results. Simulation signals with different SNR (5%, 10%, 15%, 20%, 25%, 30%) white noise and from 10 healthy volunteer 12-lead ECG signals are used to evaluate the system. The error of noisy simulation signal (SNR:30%) is under 7 points. The error of real signal is under 4 points

Keywords

electrocardiography; filtering theory; medical signal detection; medical signal processing; pattern clustering; white noise; 12-lead ECG signals; ECG character points measurement; ECG signal processing; R peak; T peak; line segment clustering technique; linear approximation distance thresholding; one beat ECG signal; simulation signals; white noise; Biomedical measurements; Character recognition; Electrocardiography; Equations; Linear approximation; Noise generators; Postal services; Signal processing; Signal to noise ratio; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE

Conference_Location

Hong Kong

ISSN

1094-687X

Print_ISBN

0-7803-5164-9

Type

conf

DOI

10.1109/IEMBS.1998.745879

Filename

745879