State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan 450001, People's Republic of China. Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450003, People's Republic of China.
Physiol Meas. 2020 Aug 21;41(7):075005. doi: 10.1088/1361-6579/ab979f.
Compressed sensing (CS) is a low-complexity compression technology that has recently been proposed. It can be applied to long-term electrocardiogram (ECG) monitoring using wearable devices. In this study, an automatic screening method for atrial fibrillation (AF) based on lossy compression of the electrocardiogram signal is proposed.
The proposed method combines the CS with the convolutional neural network (CNN). The sparse binary sensing matrix is first used to project the raw ECG signal randomly, transforming the raw ECG data from high-dimensional space to low-dimensional space to complete compression, and then using CNN to classify the compressed ECG signal involving AF. Our proposed model is validated on the MIT-BIH atrial fibrillation database.
The experimental results show that the model only needs about 1 s to complete the 24 h ECG recording of AF, which is 3.41%, 69.84% and 67.56% less than the time required by AlexNet, VGGNet and GoogLeNet, respectively. Under different compression ratios of 10% to 90%, the maximum and minimum F1 scores reach 96.25% and 88.17%, respectively.
The CS-CNN (compressed sensing convolutional neural network) model has high computational efficiency while ensuring prediction accuracy, and is a promising method for AF screening in wearable application scenarios.
压缩感知（CS）是一种低复杂度的压缩技术，最近已被提出。它可应用于使用可穿戴设备进行长期心电图（ECG）监测。在这项研究中，提出了一种基于心电图信号有损压缩的自动心房颤动（AF）筛选方法。
该方法将 CS 与卷积神经网络（CNN）相结合。首先使用稀疏二进制传感矩阵对原始 ECG 信号进行随机投影，将原始 ECG 数据从高维空间转换到低维空间以完成压缩，然后使用 CNN 对涉及 AF 的压缩 ECG 信号进行分类。我们的模型在 MIT-BIH 心房颤动数据库上进行了验证。
实验结果表明，该模型仅需约 1 秒即可完成 AF 的 24 h ECG 记录，分别比 AlexNet、VGGNet 和 GoogLeNet 所需的时间少 3.41%、69.84%和 67.56%。在 10%至 90%的不同压缩比下，最大和最小 F1 分数分别达到 96.25%和 88.17%。
CS-CNN（压缩感知卷积神经网络）模型在保证预测准确性的同时具有较高的计算效率，是可穿戴应用场景中 AF 筛选的一种有前途的方法。
