An improved cardiac arrhythmia classification using an RR interval-based approach

Rahul, Jagdeep; Sora, Marpe; Sharma, Lakhan Dev; Bohat, Vijay Kumar

doi:10.1016/j.bbe.2021.04.004

Cited by 41 publications

(12 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the elimination of high-frequency noise from unprocessed ECG data is achieved by employing, Discrete Wavelet Transform (DWT) & two Median filters. The classification of CA is done by using various classifiers like (K-NN), (SVM), (DT), and (NB) [4]. As a result, among all these classifiers SVM has obtained better results.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Precise and early detection of CA in ECG signals is very much essential as it can prevent many premature deaths [4]. Currently, Deep Neural Networks (DNN) has become a focus/advanced technique for researchers in various distinct fields including healthcare systems, where timely recognition of ECG signal variations is significantly much useful in the direction of CVDs like cardiac arrhythmia classification, valves complications which actually leads to heart attacks, strokes, etc.…”

Section: Fig: 1 Schematic Representation Of Ecg Waveformmentioning

confidence: 99%

“…These noises are prevented in pre-processing stage by employing the Discrete Wavelet Transform (DWT) and two median filters. Then it is stated that SVM and RF classifier's overall performance is better in this method and also it can be used for automatic CA classification for events like PVC and PAC beats [4].…”

Section: Fig: 1 Schematic Representation Of Ecg Waveformmentioning

confidence: 99%

See 2 more Smart Citations

Study and analysis on detection, classification, and prediction of cardiac arrhythmia using soft computing tool

Pratima,

GopalaKrishna,

Prasad

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Cardiac Arrhythmia (CA) is a disorder of heartbeat or rhythm, that happens when the electrical signals that synchronize the heartbeats do not function properly. The Electro Cardio Gram (ECG) is the electrical realization of the expanding and contracting action of the heart and can be registered easily with the electrodes placed near the chest. Hence, due to the complexity of analyzing the huge number of signals in ECG records, it has become one of the major challenges to cardiologists to make early and accurate diagnoses and prognoses. Therefore, there is an essential need for accurate automatic arrhythmia classification. According to the records of the World Health Organization (WHO), 4.5 million CA patients are reporting alone in the United States. Therefore, it is stated as one of the most common reasons for death worldwide and it is very essential to the early diagnosis and prevention of CA. Hence, this research article mainly focuses to analyse the various methods used for the classification, early diagnosis, and prevention of CA. This research presents the overview of a few research articles suggesting different methods based on various fields like IOT, Machine Learning (ML) approaches, Deep Learning (DL) approaches, and so on for the automatic detection of Cardiac Arrhythmia. The literature work mainly focuses on various early Detection, prediction, and classification techniques for CA. The research gaps were also analyzed from these papers and elaborated for further research work which can be helpful for society.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Fig: 1 Schematic Representation Of Ecg Waveformmentioning

confidence: 99%

Section: Fig: 1 Schematic Representation Of Ecg Waveformmentioning

confidence: 99%

See 1 more Smart Citation

Study and analysis on detection, classification, and prediction of cardiac arrhythmia using soft computing tool

Pratima,

GopalaKrishna,

Prasad

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Ectopic beats are defined as RR intervals shorter than 300 ms (i.e., 200 bpm) or longer than 1300 ms (i.e., 46 bpm). They might be caused by a physiological phenomenon such as premature ventricular contractions (PVC) or premature atrial contractions (PAC) [13][14][15], but most of the time they occur due to a false peak detection on PPG or ECG signals or due to a missed beat.…”

Section: Related Workmentioning

confidence: 99%

Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC)

Benchekroun

Chevallier

Istrate

et al. 2022

Sensors

View full text Add to dashboard Cite

Thanks to wearable devices joint with AI algorithms, it is possible to record and analyse physiological parameters such as heart rate variability (HRV) in ambulatory environments. The main downside to such setups is the bad quality of recorded data due to movement, noises, and data losses. These errors may considerably alter HRV analysis and should therefore be addressed beforehand, especially if used for medical diagnosis. One widely used method to handle such problems is interpolation, but this approach does not preserve the time dependence of the signal. In this study, we propose a new method for HRV processing including filtering and iterative data imputation using a Gaussian distribution. The particularity of the method is that many physiological aspects are taken into consideration, such as HRV distribution, RR variability, and normal boundaries, as well as time series characteristics. We study the effect of this method on classification using a random forest classifier (RF) and compare it to other data imputation methods including linear, shape-preserving piecewise cubic Hermite (pchip), and spline interpolation in a case study on stress. Features from reconstructed HRV signals of 67 healthy subjects using all four methods were analysed and separately classified by a random forest algorithm to detect stress against relaxation. The proposed method reached a stable F1 score of 61% even with a high percentage of missing data, whereas other interpolation methods reached approximately 54% F1 score for a low percentage of missing data, and the performance drops to about 44% when the percentage is increased. This suggests that our method gives better results for stress classification, especially on signals with a high percentage of missing data.

show abstract

“…Support vector machine and random Forest methods play essential roles in constructing machine learning classification methods with high accuracy by combining the work of this method with other techniques such as correlation technique [15] and entropy method [10]. These techniques increased the classification accuracy and robustness against the unbalancing problem.…”

Section: Introductionmentioning

confidence: 99%

Efficient ECG Beats Classification Techniques for The Cardiac Arrhythmia Detection Based on Wavelet Transformation

2023

IJIES

View full text Add to dashboard Cite

Arrhythmia is one of the cardiovascular disease types that affect humans and often leads to death. generally, ECG signals uses to diagnose the patient's heart state where the ECG illustrates the electrical activities and physiological state of the heart. This paper proposes ECG classification model to classify four types of heartbeats for the early detection of Arrhythmia. Detail wavelet coefficients of ECG were extracted using discrete wavelet transform (DWT) to produce new datasets of ECG with for the dimensions and processed information to ensure the efficiency of proposed classification techniques. In addition, power spectral density (PSD) has been calculated for approximate wavelet coefficients of ECG to extract more relevant features that improve the performance of the classifier. The two classifier models use, the convolution neural network (CNN) utilizes for deep learning networks with artificial neural network (ANN) and the Random forest ensemble method. The experiments and results show that, the proposed model with RF archives 98.5% classification accuracy considering all decomposition levels of DWT. Additionally, the solution with CNN-ANN achieves 96% classification accuracy at the third decomposition level. Therefore, the results show the impact of the proposed solution with high efficiency in terms of fewer dimensions and high accuracy.

show abstract

An improved cardiac arrhythmia classification using an RR interval-based approach

Cited by 41 publications

References 55 publications

Study and analysis on detection, classification, and prediction of cardiac arrhythmia using soft computing tool

Study and analysis on detection, classification, and prediction of cardiac arrhythmia using soft computing tool

Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC)

Efficient ECG Beats Classification Techniques for The Cardiac Arrhythmia Detection Based on Wavelet Transformation

Contact Info

Product

Resources

About