A multi-wavelet optimization approach using similarity measures for electrocardiogram signal classification

Nazarahari, Milad; Namin, Sahand Ghorbanpour; Markazi, Amir H.D.

doi:10.1016/j.bspc.2015.04.010

Cited by 25 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in [8, 9, 12, 13], we use NNs to discriminate between the different types of beats according to their respective application. The multilayer NNs have been a great tool for classification purposes; they are powerful and their deep learning extension (state of the art for complicated problems like image classification and object detection on images) has put them into a powerful place to solve many problems.…”

Section: Resultsmentioning

confidence: 99%

“…For research purposes, along with the MIT-BIH arrhythmia database, the PhysioNet web page provides a file for every ECG record with a beat classification. We relabeled this database for this work in a similar way as in [8–16]. We kept the original labels of NB and PVC, and we mapped the rest of the heartbeats as “Others Beats” (OB).…”

Section: Methodsmentioning

confidence: 99%

“…Since the new algorithms are increasingly more powerful and precise, gaps between the use of recent algorithms and the standard analysis methodology of the available evidence have begun to emerge [5–7]. Nazarahari et al [8] used a neural network (NN) to classify six relevant types of heartbeats from a set of features created by new wavelet functions along with different distances and principal component analysis (PCA) to reduce the dimensionality. Martis et al [9] applied the bispectrum computation in each beat and PCA to create the features that ultimately fed NN and support vector machines (SVMs) algorithms to classify between five types of heartbeats including the normal heartbeats (NBs) and premature ventricular contraction (PVC) beats.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian Classification Models for Premature Ventricular Contraction Detection on ECG Traces

Casas

Avitia

González-Navarro

et al. 2018

Journal of Healthcare Engineering

View full text Add to dashboard Cite

According to the American Heart Association, in its latest commission about Ventricular Arrhythmias and Sudden Death 2006, the epidemiology of the ventricular arrhythmias ranges from a series of risk descriptors and clinical markers that go from ventricular premature complexes and nonsustained ventricular tachycardia to sudden cardiac death due to ventricular tachycardia in patients with or without clinical history. The premature ventricular complexes (PVCs) are known to be associated with malignant ventricular arrhythmias and sudden cardiac death (SCD) cases. Detecting this kind of arrhythmia has been crucial in clinical applications. The electrocardiogram (ECG) is a clinical test used to measure the heart electrical activity for inferences and diagnosis. Analyzing large ECG traces from several thousands of beats has brought the necessity to develop mathematical models that can automatically make assumptions about the heart condition. In this work, 80 different features from 108,653 ECG classified beats of the gold-standard MIT-BIH database were extracted in order to classify the Normal, PVC, and other kind of ECG beats. Three well-known Bayesian classification algorithms were trained and tested using these extracted features. Experimental results show that the F1 scores for each class were above 0.95, giving almost the perfect value for the PVC class. This gave us a promising path in the development of automated mechanisms for the detection of PVC complexes.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian Classification Models for Premature Ventricular Contraction Detection on ECG Traces

Casas

Avitia

González-Navarro

et al. 2018

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Then, the multi-resolution analysis can be realized in both low frequency band and high frequency band. Thus, ensemble multiwavelet analysis method is a more precise and comprehensive vibration data processing tool than the multiwavelet transform [ 18 , 32 , 33 , 34 ]. Let l be the transform level and

be the ensemble multiwavelet transform coefficients at the

decomposition in the

frequency band.…”

Section: Ensemble Multiwavelet Analysis Methodsmentioning

confidence: 99%

Fault Diagnosis of Demountable Disk-Drum Aero-Engine Rotor Using Customized Multiwavelet Method

Chen

Wang

et al. 2015

Sensors

View full text Add to dashboard Cite

The demountable disk-drum aero-engine rotor is an important piece of equipment that greatly impacts the safe operation of aircraft. However, assembly looseness or crack fault has led to several unscheduled breakdowns and serious accidents. Thus, condition monitoring and fault diagnosis technique are required for identifying abnormal conditions. Customized ensemble multiwavelet method for aero-engine rotor condition identification, using measured vibration data, is developed in this paper. First, customized multiwavelet basis function with strong adaptivity is constructed via symmetric multiwavelet lifting scheme. Then vibration signal is processed by customized ensemble multiwavelet transform. Next, normalized information entropy of multiwavelet decomposition coefficients is computed to directly reflect and evaluate the condition. The proposed approach is first applied to fault detection of an experimental aero-engine rotor. Finally, the proposed approach is used in an engineering application, where it successfully identified the crack fault of a demountable disk-drum aero-engine rotor. The results show that the proposed method possesses excellent performance in fault detection of aero-engine rotor. Moreover, the robustness of the multiwavelet method against noise is also tested and verified by simulation and field experiments.

show abstract

“…Another issue about how to train the structure is the loss function as shown in formula (9), which is essentially the same as the negative L (Q) in formula (7). In the view of training, the losses of a VAE come from two aspects: the first part is from the neural network that measures how much the difference between the reconstructed data and the original input.…”

Section: Variational Autoencodermentioning

confidence: 99%

Electrocardiogram Recognization Based on Variational AutoEncoder

Chen¹,

Meng²,

Qing³

2018

Machine Learning and Biometrics

View full text Add to dashboard Cite

Subtle distortions on electrocardiogram (ECG) can help doctors to diagnose some serious larvaceous heart sickness on their patients. However, it is difficult to find them manually because of disturbing factors such as baseline wander and high-frequency noise. In this chapter, we propose a method based on variational autoencoder to distinguish these distortions automatically and efficiently. We test our method on three ECG datasets from Physionet by adding some tiny artificial distortions. Comparing with other approaches adopting autoencoders [e.g., contractive autoencoder, denoising autoencoder (DAE)], the results of our experiment show that our method improves the performance of publically available on ECG analysis on the distortions.

show abstract

A multi-wavelet optimization approach using similarity measures for electrocardiogram signal classification

Cited by 25 publications

References 31 publications

Bayesian Classification Models for Premature Ventricular Contraction Detection on ECG Traces

Bayesian Classification Models for Premature Ventricular Contraction Detection on ECG Traces

Fault Diagnosis of Demountable Disk-Drum Aero-Engine Rotor Using Customized Multiwavelet Method

Electrocardiogram Recognization Based on Variational AutoEncoder

Contact Info

Product

Resources

About