Objective: A novel electrocardiogram (ECG) classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. Methods: The proposed solution employs a novel architecture consisting of wavelet transform and multiple long short-term memory (LSTM) recurrent neural networks (see Fig. 1). Results: Experimental evaluations show superior ECG classification performance compared to previous works. Measurements on different hardware platforms show the proposed algorithm meets timing requirements for continuous and real-time execution on wearable devices. Conclusion: In contrast to many compute-intensive deep-learning based approaches, the proposed algorithm is lightweight, and therefore, brings continuous monitoring with accurate LSTM-based ECG classification to wearable devices. Significance: The proposed algorithm is both accurate and lightweight. The source code is available online at http://lis.ee.sharif.edu.

中文翻译：

---

基于LSTM的ECG分类，可对个人可穿戴设备进行连续监控

客观的：提出了一种新颖的心电图（ECG）分类算法，用于对处理能力有限的可穿戴设备进行连续心脏监测。 方法：提出的解决方案采用了一种由小波变换和多个长期短期记忆（LSTM）递归神经网络组成的新颖架构（请参阅 图。1）。 结果：实验评估表明，与以前的作品相比，ECG的分类性能更高。在不同硬件平台上的测量结果表明，该算法满足可穿戴设备连续和实时执行的时序要求。结论：与许多基于计算密集型深度学习的方法相比，本文提出的算法是轻量级的，因此，可穿戴设备通过基于LSTM的精确ECG分类进行连续监控。 意义：提出的算法既准确又轻巧。源代码可从以下位置在线获得：http://lis.ee.sharif.edu。