Long-term Wearable Electrocardiogram Signal Monitoring and Analysis Based on Convolutional Neural Network

Abstract

Wearable devices are increasingly popular for health monitoring via electrocardiograms (ECGs) as they can portably monitor heart conditions over a long time. However, so far there are no publicly available ECG data sets collected from wearable devices. Most ECG analysis algorithms target ECG data collected by hospital equipment. In the present study, we used the IREALCARE2.0 Flexible Cardiac Monitor Patch as the wearable device to collect ECG signals and formed ECG data sets. Wearable ECG data tended to contain more interference and be large in size. This article proposed a deep CNN approach, named time–spatial convolutional neural networks (TSCNNs), for the automatic classification and analysis of ECG signals from wearable devices. First, the original long-term ECG signals were divided into separate heartbeats and input into the TSCNN. Second, we applied convolution over time and spatial filtering for each heartbeat to extract abundant features. Finally, the cascaded small-scale kernel convolution was applied to improve classification performance and reduce the number of network parameters. To avoid overfitting, some regularized methods such as dropout and batch normalization were adopted. In the experiments, the method proposed in this letter is compared with other eight ECG classification algorithms. Our method attained the highest classification accuracy. The experimental results indicated that the proposed method can achieve better performance for wearable ECG data and can effectively monitor whether the wearer has an abnormal ECG.