You are viewing a javascript disabled version of the site. Please enable Javascript for this site to function properly.
Go to headerGo to navigationGo to searchGo to contentsGo to footer
In content section. Select this link to jump to navigation

Quick detection of QRS complexes and R-waves using a wavelet transform and K-means clustering

Issue title: Frontiers in Biomedical Engineering and Biotechnology – Proceedings of the 4th International Conference on Biomedical Engineering and Biotechnology, 18–21 August 2015, Shanghai, China

Guest editors: Feng Liu, Dong-Hoon Lee, Ricardo Lagoa and Sandeep Kumar

Article type: Research Article

Authors: Xia, Yong; * | Han, Junze | Wang, Kuanquan

Affiliations: Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Correspondence: [*] Address for correspondence: Yong Xia, Department of Computer Science and Technology, Harbin Institute of Technology, West Da Zhi St., Harbin, P.C. 150001, China. Tel.: +86 631 5687921; Fax: +86 631 5687927; E-mail: [email protected].

Keywords: ECG, detection of QRS-complex and R-wave, wavelet transform, k-means clustering

DOI: 10.3233/BME-151402

Journal: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S1059-S1065, 2015

Published: 2015
Get PDF open access

Based on the idea of telemedicine, 24-hour uninterrupted monitoring on electrocardiograms (ECG) has started to be implemented. To create an intelligent ECG monitoring system, an efficient and quick detection algorithm for the characteristic waveforms is needed. This paper aims to give a quick and effective method for detecting QRS-complexes and R-waves in ECGs. The real ECG signal from the MIT-BIH Arrhythmia Database is used for the performance evaluation. The method proposed combined a wavelet transform and the K-means clustering algorithm. A wavelet transform is adopted in the data analysis and preprocessing. Then, based on the slope information of the filtered data, a segmented K-means clustering method is adopted to detect the QRS region. Detection of the R-peak is based on comparing the local amplitudes in each QRS region, which is different from other approaches, and the time cost of R-wave detection is reduced. Of the tested 8 records (total 18201 beats) from the MIT-BIH Arrhythmia Database, an average R-peak detection sensitivity of 99.72 and a positive predictive value of 99.80% are gained; the average time consumed detecting a 30-min original signal is 5.78s, which is competitive with other methods.

Show more