The lightweight 1D-CNN model (CNN5) achieved an average accuracy of 83.9% and an AUC of 0.898 for detecting atrial fibrillation on a resource-constrained edge device.
Does a 1D-CNN model deployed on an edge device accurately detect AFib with acceptable latency compared to cloud computing?
A 1D-CNN architecture deployed on edge devices offers a potential low-cost, continuous monitoring solution for atrial fibrillation detection, though specific performance results were not included in the provided text.
Atrial Fibrillation (AFib) is a common cardiac arrhythmia whose global prevalence has risen in recent years. If left untreated, AFib can lead to severe complications such as stroke and heart failure. Because AFib may occur without symptoms, continuous monitoring is critical for timely detection. This paper presents a low-cost Intelligent Health Monitoring System (IHMS) that uses one-dimensional Convolutional Neural Networks (1D-CNNs) to detect AFib from Electrocardiogram (ECG) signals. The study evaluates the feasibility of deploying 1D-CNN models on resource-constrained edge devices and compares edge- and cloud-based computing architectures with respect to inference efficiency. Three 1D-CNN models of increasing complexity are designed, trained, and tested on datasets containing AFib and Normal Sinus Rhythm (NSR) segments. Two experiments are conducted to assess end-to-end delay and prediction time under a controlled experimental setup. The results demonstrate the potential for on-device AFib detection in constrained environments and provide practical insights into selecting suitable architectures for embedded deployment.
Nordin et al. (Mon,) conducted a other in Atrial Fibrillation (n=25). 1D-Convolutional Neural Network (1D-CNN) on Edge Device vs. Cloud-based computing architecture was evaluated on AFib classification accuracy and AUC. The lightweight 1D-CNN model (CNN5) achieved an average accuracy of 83.9% and an AUC of 0.898 for detecting atrial fibrillation on a resource-constrained edge device.