article · IEEE Access
Automated classification of heart conditions from electrocardiogram (ECG) signals often faces challenges due to imbalanced data. A deep learning framework addresses this by classifying ECG arrhythmia plot images using two distinct architectures: a custom lightweight convolutional neural network with three convolutional layers, and a fine-tuned MobileNet-V2 transfer learning model. Raw signals undergo noise reduction using a Butterworth filter followed by beat segmentation through R-peak detection. To tackle the problem of underrepresented arrhythmia classes in the benchmark MIT-BIH dataset, an auxiliary classifier generative adversarial network is used to generate synthetic training data across four heartbeat types. Evaluation shows that the lightweight network achieves an average classification accuracy of 99.22 percent, while the fine-tuned MobileNet-V2 achieves 98.69 percent accuracy. Both approaches show strong capability in identifying diverse irregular heart rhythms.
Cardiovascular monitoring relies heavily on accurate interpretation of heart rhythms, but automated systems often fail when specific arrhythmia types are rarely seen in training data. Developing lightweight models that operate accurately on filtered and balanced heartbeat signals supports more reliable automated diagnostic tools for cardiovascular healthcare.
The lightweight architectures could enable automated arrhythmia detection tools for clinical software or portable cardiac monitoring devices. The primary intended users are healthcare providers and medical technology developers. The work represents applied research tested on a benchmark dataset, meaning further clinical validation on real-world patient data would be required before diagnostic deployment.
AI-generated from the published abstract. Always read the original work before citing.
Arrhythmia detection in electrocardiogram (ECG) signals is a vital aspect of cardiovascular health monitoring. Current automated methods for arrhythmia classification often struggle to attain satisfactory performance in the detection of various heart conditions, particularly when dealing with imbalanced datasets. This study introduces a novel deep learning approach for the detection and classification of ECG arrhythmia plot images. Our methodology features a Lightweight Custom Convolutional Neural Network model(LC-CNN), comprising just three convolutional layers and a transfer learning model with MobileNet-V2 architecture that leverages pre-trained features to enhance arrhythmia classification. Data preprocessing of the ECG signals involving noise reduction with a Butterworth filter and precise beat segmentation via R-peak detection, ensure high-quality input for our model. Furthermore, a notable contribution for ECG data augmentation, adopting the implementation of an Auxiliary Classifier Generative Adversarial Network (ACGAN), specifically addressing class imbalance in the benchmark MIT-BIH dataset to classify four types of ECG heartbeats. This approach enriches the dataset, enhancing the models’ ability to detect underrepresented arrhythmia classes. The proposed system demonstrates an impressive average classification accuracy achieving 99.22% using the LC-CNN model. Closely followed by the fine-tuned MobileNet-V2 model with 98.69% accuracy, outperforming other methods and underscoring its effectiveness when faced with diverse irregular heartbeats and arrhythmia.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3378730
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
