Abstract
This paper aims at proposing an abnormality detection framework for electrocardiogram (ECG) signals, which owns unbalance distribution among different classes and gaining high accuracy in rhythm/morphology abnormalities classification. The proposed framework is composed of two models: data augmentation model and classification model. In this framework, data augmentation model is designed to recast a class-balanced training dataset by generating artificial data of minor class. The outputs of augmentation model are transferred into classification model. The classification model is designed to identify abnormalities accurately after training using both the experimental and generated datasets. Data augmentation model is supported by auxiliary classifier generative adversarial network (ACGAN). We construct Generator and Discriminator of the ACGAN by stacking multiple 1-dimensional convolutional layers with small kernel size. Dropout function and batch normalization are added to prevent gradients vanish and speed up convergence. In order to evaluate the performance of augmentation model, a set of quantitative indicators are introduced to verify the quality of generated ECG signals. We establish classification model based on stacked residual network parallel connected with long short-term memory (LSTM) network. The experimental study is conducted for single heartbeat detection and consecutive heartbeat detection. The results based on standard benchmark, MIT-BIH, and competition database provided by 2018 China physiological signal challenge (CPSC) have verified the proposed framework can achieve high performance in robustness and accuracy for class-imbalanced dataset.
Highlights
In recent years, the incidence of cardiovascular diseases (CVDs) has exploded due to multiple factors such as population ageing, chronic cardiovascular disease and increasing living pressures
Considering ECG signals are time-series signals, we combine long short-term memory (LSTM) network with residual network to achieve a better performance in features learning
The competition database provided by 2018 China Physiological Signal Challenge (CPSC) is applied for consecutive-beats detection
Summary
The incidence of cardiovascular diseases (CVDs) has exploded due to multiple factors such as population ageing, chronic cardiovascular disease and increasing living pressures. Heart disease has become a major threat to human life [1], [2]. Detecting abnormalities of ECG signals has often been applied in clinical CVDs diagnosis [3], [4]. The majority of extant models for rhythm/morphology abnormalities detection [5], [6] are comprised by four independent steps: 1) ECG signals acquisition; 2) data processing; 3) features extraction; 4) identification. Deep learning-based approach which ensembles feature extraction and classification into one process has been successfully applied for ECG signal analysis to overcome this challenge. Deep learning-based ECG signal processing framework has powerful feature extraction ability which can learn deep features from given signals and optimize model automatically to achieve high accuracy in classification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
