Electrocardiogram beat classification using empirical mode decomposition and multiclass directed acyclic graph support vector machine

Saini, Indu; Singh, Dilbag; Khosla, Arun

doi:10.1016/j.compeleceng.2014.04.004

Cited by 29 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM, which was developed by Vapnik [40], has been widely applied in ECG classification studies [23,25,28,29]. SVM finds a hyperplane in a high-dimensional space by separating the training samples of each class or by maximizing the minimum distance between the hyperplane and training samples.…”

Section: Methodsmentioning

confidence: 99%

“…Valenza proposed a personalized probabilistic framework wherein features were derived from instantaneous spectrum and bispectrum; an SVM classifier was applied in heartbeat recognition [28]. In a previous study, multiclass-directed acyclic graph SVM was implemented on feature vectors utilising empirical mode decomposition and singular value decomposition for ECG classification [29]. Kamath studied ECG beats from the energy perspective by extracting features from the nonlinear component in time and frequency domains via the Teager energy operator and used an NN as a classifier to identify the five classes of ECG beats [30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Yuan

Wang

et al. 2016

Sensors

View full text Add to dashboard Cite

Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Yuan

Wang

et al. 2016

Sensors

View full text Add to dashboard Cite

show abstract

“…Other research was done in classification of the ECG signals based on the distinguishable features of different heart arrhythmias [24]. They proposed a new method of classification based on the multiclass support vector machine (SVM); it was called directed acyclic graph support vector machine (DAGSVM).…”

Section: Different Methods For Detecting Af Have Been Developed By Comentioning

confidence: 99%

“…Then classification accuracy was evaluated by automatically detecting the best discriminating features and by determining the best required model amongst three kernel functions: linear, polynomial, and radial basis function. Empirical mode decomposition and singular value decomposition were used to extract and select the features [24]. Then cross-validation and particle swarm optimization (PSO) were used to optimize performance in terms of classification accuracy by selecting the best model and by estimating the best parameters of the SVM classifier.…”

Section: Different Methods For Detecting Af Have Been Developed By Comentioning

confidence: 99%

Evolutionary optimisation of atrial fibrillation diagnostic algorithms

Smiley

2016

IJSI

View full text Add to dashboard Cite

The goal of this research is to introduce an improved method for detecting atrial fibrillation (AF). The foundation of our algorithm is the irregularity of the RR intervals in the electrocardiogram (ECG) signal, and their correlation with AF. Three statistical techniques, including root mean squares of successive differences (RMSSD), turning points ratio (TPR), and Shannon entropy (SE), are used to detect RR interval irregularity. We use the Massachusetts Institution of Technology / Beth Israel Hospital (MIT-BIH) atrial fibrillation databases and their annotations to tune the parameters of the statistical methods by biogeography-based optimization (BBO), which is an evolutionary optimization algorithm. We trained each statistical method to diagnose AF on each database. Then each trained method was tested on the rest of the databases. We were able to obtain accuracy levels as high as 99% for the detection of AF in the trained databases. We obtained accuracy levels of up to 75% in the tested databases. v

show abstract

“…In addition, studies have explored a Support Vector Machine (SVM) for AF detection. SVM is a reliable classification method and has been proved to provide good performances in various medical diagnostics (Nuryani et al, 2012;Saini et al, 2014;Suchetha et al, 2013). In varied applications, SVM outperforms other algorithms (Foley et al, 2012;Saleh et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Atrial fibrillation detection using support vector machine and electrocardiographic descriptive statistics

Nuryani

Harjito

Yahya

et al. 2017

IJBET

View full text Add to dashboard Cite

This paper proposes a new technique for detecting atrial fibrillation (AF). The method employs electrocardiographic features and support vector machine (SVM). The features include descriptive statistics of electrocardiographic RR interval. The RR interval is the distance in time between two consecutive R-peaks of electrocardiogram. AF detections using SVM with different electrocardiographic features and different SVM free parameters are explored. Employing SVM with the optimal free parameters and all the proposed electrocardiographic features, we find an AF detection technique with a comparable performance. The best performance obtained by the technique is 98.47% and 97.84%, in terms of sensitivity and specificity.

show abstract

Electrocardiogram beat classification using empirical mode decomposition and multiclass directed acyclic graph support vector machine

Cited by 29 publications

References 19 publications

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Evolutionary optimisation of atrial fibrillation diagnostic algorithms

Atrial fibrillation detection using support vector machine and electrocardiographic descriptive statistics

Contact Info

Product

Resources

About