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

Abstract

Abstract. 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.

Association between heart rate variability indices and features of spontaneous ventricular tachyarrhythmias in mice

“…The GUI program developed by Matlab 2014a (The MathWorks) was applied to detect R peaks automatically by which ectopic beats were identified and HRV analyzed. Furthermore, R peaks were detected using a wavelet transform and K‐means clustering 35 . All ectopic beats were firstly automatically detected using a combined method of improved impulse rejection filter and template matching 36 .…”

Investigating the effect of traditional Persian music on ECG signals in young women using wavelet transform and neural networks

“…There is no special method for selecting a certain wavelet. Choosing a wavelet family, which closely matches the signal to be processed, play an important role in wavelet applications (12). As shown in Figure 1, the Daubechies wavelet family is similar in shape to the QRS complex.…”

An IoT-Based Computational Framework for Healthcare Monitoring in Mobile Environments

“…First, the overall activity must be properly broken down into tasks and data flows. As a simple example of the functions that take place in ECGs analysis [ 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 ], the following tasks are defined according the scheme depicted in Figure 3 a. Other tasks and operation may be needed for each of the previous diagnosis methods.…”

“…For example, the Hilbert transform allows to detect the R peak and to segment the morphology of QRS complex along the ECG [ 95 ]. A wide range of methods allowing high detection rates have been proposed, and recently, there are research works for achieving a real-time detection process in order to run this ECG analysis applications into wearable biosensors [ 90 , 91 , 92 , 93 ].…”

“…The design of the test is based on the results of previous research works [ 88 , 93 , 103 , 104 ] and on our own estimations. In addition, recent methods that propose a real-time segmentation and feature extraction have been reviewed in order to get an improved implementation for wearable and mobile devices [ 90 , 91 , 92 , 93 ]. The validation of these methods is usually produced in term of Sensitivity in detecting anomaly behaviours.…”