A Novel Method to Detect Multiple Arrhythmias Based on Time-Frequency Analysis and Convolutional Neural Networks

Wu, Ziqian; Lan, Tianjie; Yang, Cuiwei; Nie, Zedong

doi:10.1109/access.2019.2956050

Cited by 33 publications

(22 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formally, given a signal

, the CWT is defined as

where a is a scale parameter, b is a translation parameter, and

is the wavelet function (also known as mother wavelet). The scale can be converted to frequency by

where

is the center frequency of the mother wavelet,

is the sampling frequency of signal

[ 26 ].…”

Section: Methodsmentioning

confidence: 99%

“…The pooling layer, also known as the subsampling layer, is used to reduce the feature dimension and speed up the training process. The action of this layer is to calculate the average or maximum convolution features within adjacent neurons placed in the previous convolution layer [ 26 ]. The last layer of CNN is normally connected to one or more fully connected neurons that use to compute the class scores.…”

Section: Methodsmentioning

confidence: 99%

“…where F c is the center frequency of the mother wavelet, f s is the sampling frequency of signal x(t) [26]. Among them, the choice of mother wavelet is often critical to the effect of timefrequency analysis.…”

Section: Time-frequency Scalogram Via Cwtmentioning

confidence: 99%

See 2 more Smart Citations

Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Wang

Sun

et al. 2021

Entropy

184

View full text Add to dashboard Cite

Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75%, 67.47%, 68.76%, and 98.74% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75~16.85%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool.

show abstract

“…Formally, given a signal

, the CWT is defined as

where a is a scale parameter, b is a translation parameter, and

is the wavelet function (also known as mother wavelet). The scale can be converted to frequency by

where

is the center frequency of the mother wavelet,

is the sampling frequency of signal

[ 26 ].…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Wang

Sun

et al. 2021

Entropy

184

View full text Add to dashboard Cite

show abstract

“…SVMs models with various feature types have been extensively used for ECG classification [10,6,3,5] yet such models suffer from the computational complexity of the SVM algorithm. On the other hand, many recent works proposed various topologies of 1D and 2D CNNs in conjunction with different feature spaces for ECG classification [11,12,13,11,3,5]. The common theme between these works is using the STFT spectrogram accompanied with 2D CNN models to enhance the ECG classification results.…”

Section: Literature Reviewmentioning

confidence: 99%

A Self-Contained STFT CNN for ECG Classification and Arrhythmia Detection at the Edge

Farag

2022

IEEE Access

View full text Add to dashboard Cite

Automated classification of Electrocardiogram (ECG) for arrhythmia monitoring is the core of cardiovascular disease diagnosis. Machine Learning (ML) is widely used for arrhythmia detection using various feature engineering and classification models. Cloud-based inference is the prevailing deployment model of modern ML algorithms which does not always meet the availability and privacy requirements of ECG monitoring. Edge inference is an emerging alternative which addresses the concerns of latency, privacy, connectivity, and availability. However, edge deployment of AI models is challenging due to the demanding requirements of modern ML algorithms and the computation constraints of edge devices. In this work, we propose a lightweight self-contained short-time Fourier Transform (STFT) Convolutional Neural Network (CNN) model for ECG classification and arrhythmia detection in real-time at the edge. We provide a clear interpretation of the convolutional layer as a Finite Impulse Response (FIR) filter and exploit this interpretation to develop an STFT-based 1D convolutional (Conv1D) layer to extract the spectrogram of the input ECG signal. The Conv1D output feature maps are reshaped into a 2D heatmap and fed to a 2D convolutional (Conv2D) neural network (CNN) for classification. The real-time performance of the proposed model is planned in advance to fit the resource constraints of edge inference. Four model variants are trained, optimized, and tested on a raspberry-pi edge device. Weight quantization and pruning techniques are applied to the developed models to optimize them for edge computing. The MIT-BIH arrhythmia database is used for model training and testing. The proposed classifiers can achieve up to 99.1% classification accuracy and 95% F1-score at the edge with a maximum model size of 90 KB, an average inference time of 9 ms, and a maximum memory usage of 12 MB. The achieved results of the proposed classifier enable its deployment on a wide range of edge devices for arrhythmia detection.

show abstract

“…Deep learning methods have the capability to automatical-ly learn features from input signals and can extract more abstract and advanced features [12]. Therefore, recently many studies use deep learning methods to design ECG classifiers [13][14][15][16][17][18][19][20] and achieved better performance than traditional methods.…”

Section: Introductionmentioning

confidence: 99%

ProEGAN-MS: A Progressive Growing Generative Adversarial Networks for Electrocardiogram Generation

et al. 2021

View full text Add to dashboard Cite

Electrocardiogram (ECG) is a physiological signal widely used in monitoring heart health, which is of great significance to the detection and diagnosis of heart diseases. Because abnormal heart rhythms are very rare, most ECG datasets have data imbalance problems. At present, many algorithms for ECG anomaly automatic recognition are affected by data imbalance. Conventional data augmentation methods are not suitable for the augmentation of the ECG signal, because the ECG signal is one-dimensional and their morphology has physiological significances. In this paper, we propose a ProGAN based ECG sample generation model, called ProEGAN-MS, to solve the problem of data imbalance. The model can stably generate realistic ECG samples. We evaluate the fidelity and diversity of the data generated by the model and compare the data distribution of the original and generated data. In addition, in order to show the diversity of the generated ECG data more intuitively, we manually checked the diversity and calculate the statistics of the data. The results show that compared with other ECG augmentation methods based on GANs, the ECG data generated by our model has higher fidelity and diversity, and the distribution of generated samples is closer to the distribution of original data. Finally, we established neural network models for arrhythmia classification, and used them to evaluate the improvement of the classification model performance by ProEGAN-MS. The results show that augmented data by ProEGAN-MS can effectively improve the insufficient sensitivity and precision of the classification model.

show abstract

A Novel Method to Detect Multiple Arrhythmias Based on Time-Frequency Analysis and Convolutional Neural Networks

Cited by 33 publications

References 38 publications

Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

A Self-Contained STFT CNN for ECG Classification and Arrhythmia Detection at the Edge

ProEGAN-MS: A Progressive Growing Generative Adversarial Networks for Electrocardiogram Generation

Contact Info

Product

Resources

About