K-means algorithm for the detection and delineation of QRS-complexes in Electrocardiogram

Mehta, S. S.; Shete, Deepak; Lingayat, N. S.; Chouhan, V. S.

doi:10.1016/j.irbm.2009.10.001

Cited by 66 publications

(30 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods are based on derivative-based algorithms (Holsinger et al 1971), filtering approaches (digital filters (Yu et al 1985), adaptive filters (Soria et al 1998)), mathematical transformations (wavelet (Li C et al 1995, Martinez J P et al 2004, Dumont et al 2010, filter banks (Afonso et al 1999), phasor transform (Martinez A et al 2010)), classification methods (neural network approaches (Hu et al 1993), support vector machine (SVM) (Mehta et al 2008), fuzzy C-means algorithm (Mehta et al 2009)), hidden Markov models (HMM) (Coast et al 1990, Hughes et al 2004a, Hughes et al 2006, Andreao et al 2006a, Andreao et al 2006b, automated method (Christov et al 2007) and mathematical morphology methods (Sun et al 2005). Adaptive filters, wavelet transform, SVM, mathematical morphology methods, HMM and Partially Collapsed Gibbs Sampler (PCGS) (Lin et al 2010, Lin et al 2011a have also been used for P-and T-wave delineation.…”

Section: Introductionmentioning

confidence: 99%

ECG denoising and fiducial point extraction using an extended Kalman filtering framework with linear and nonlinear phase observations

Akhbari¹,

Shamsollahi²,

Jutten³

et al. 2016

Physiol. Meas.

View full text Add to dashboard Cite

Abstract. In this paper we propose an efficient method for denoising and extracting fiducial point (FP) of ECG signals. The method is based on a nonlinear dynamic model which uses Gaussian functions to model ECG waveforms. For estimating the model parameters, we use an extended Kalman filter (EKF). In this framework called EKF25, all the parameters of Gaussian functions as well as the ECG waveforms (P-wave, QRS complex and T-wave) in the ECG dynamical model, are considered as state variables. In this paper, the dynamic time warping method is used to estimate the nonlinear ECG phase observation. We compare this new approach with linear phase observation models. Using linear and nonlinear EKF25 for ECG denoising and nonlinear EKF25 for fiducial point extraction and ECG interval analysis are the main contributions of this paper. Performance comparison with other EKF-based techniques shows that the proposed method results in higher output SNR with an average SNR improvement of 12 dB for an input SNR of -8 dB. To evaluate the FP extraction performance, we compare the proposed method with a method based on partially collapsed Gibbs sampler and an established EKF-based method. The mean absolute error and the root mean square error of all FPs, across all databases are 14 msec and 22 msec, respectively, for our proposed method, with an advantage when using a nonlinear phase observation. These errors are significantly smaller than errors obtained with other methods. For ECG interval analysis, with an absolute mean error and a root mean square error of about 22 msec and 29 msec, the proposed method achieves better accuracy and smaller variability with respect to other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

ECG denoising and fiducial point extraction using an extended Kalman filtering framework with linear and nonlinear phase observations

Akhbari¹,

Shamsollahi²,

Jutten³

et al. 2016

Physiol. Meas.

View full text Add to dashboard Cite

show abstract

“…It is based on the minimization of the performance index, which is defined as the sum of the squared distances from all points in a cluster domain to the cluster center [5]. QRS regions in a relatively short time interval have more characteristics in common.…”

Section: Detection Of Qrs-complexes Using K-means Clustering On Segmementioning

confidence: 99%

“…Fanga proposed a novel algorithm based on the phase space trajectory of ECG [4]. Better results can be obtained based on machine learning and morphology theory [5][6][7][8], but it is very difficult to meet real-time application using these complicated algorithms. Therefore, new, more efficient algorithms need to be presented [9,10].…”

Section: Introductionmentioning

confidence: 99%

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

Xia

Han

Wang

2015

BME

View full text Add to dashboard Cite

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.

show abstract

“…So far, variant methods for ECG de-noising and R-wave detection have been proposed, including approaches of derivatives [10,11], digital filters [12][13][14][15], wavelet transform(WT) [1,[16][17][18][19][20][21][22][23][24][25][26], artificial neural network (ANN) [27,28], support vector machine (SVM) [29], k-means [30], empirical mode decomposition (EMD) [31], geometrical matching [32][33][34], combined threshold method [35,36], phase space method [37], Hilbert Transform method [38], and mixed approach [39,40]. Almost all of the methods listed above have some limitations.…”

Section: Introductionmentioning

confidence: 99%

“…The performance of the modified method has shown better detection performance, but it is not sensitive to the change of the integral information of QRS, leading to mistakes in the cases of low-amplitude QRS, sudden change of amplitude and high P and T waves. Other methods based on cluster such as K-means have a similar problem and cost enormous computation time because of the need of calculation over the whole sample set, which makes it unrealistic for the real-time detection [30].…”

Section: Introductionmentioning

confidence: 99%

A novel method for the detection of R-peaks in ECG based on K-Nearest Neighbors and Particle Swarm Optimization

Rui

Wang

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Cardiovascular diseases are associated with high morbidity and mortality. However, it is still a challenge to diagnose them accurately and efficiently. Electrocardiogram (ECG), a bioelectrical signal of the heart, provides crucial information about the dynamical functions of the heart, playing an important role in cardiac diagnosis. As the QRS complex in ECG is associated with ventricular depolarization, therefore, accurate QRS detection is vital for interpreting ECG features. In this paper, we proposed a real-time, accurate, and effective algorithm for QRS detection. In the algorithm, a proposed preprocessor with a band-pass filter was first applied to remove baseline wander and power-line interference from the signal. After denoising, a method combining K-Nearest Neighbor (KNN) and Particle Swarm Optimization (PSO) was used for accurate QRS detection in ECGs with different morphologies. The proposed algorithm was tested and validated using 48 ECG records from MIT-BIH arrhythmia database (MITDB), achieved a high averaged detection accuracy, sensitivity and positive predictivity of 99.43, 99.69, and 99.72%, respectively, indicating a notable improvement to extant algorithms as reported in literatures.

show abstract

K-means algorithm for the detection and delineation of QRS-complexes in Electrocardiogram

Cited by 66 publications

References 20 publications

ECG denoising and fiducial point extraction using an extended Kalman filtering framework with linear and nonlinear phase observations

ECG denoising and fiducial point extraction using an extended Kalman filtering framework with linear and nonlinear phase observations

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

A novel method for the detection of R-peaks in ECG based on K-Nearest Neighbors and Particle Swarm Optimization

Contact Info

Product

Resources

About