论文标题
一种生成的对抗方法，用于心电图合成和降解
A Generative Adversarial Approach To ECG Synthesis And Denoising
论文作者
论文摘要
已知生成的对抗网络（GAN）产生的合成数据很难被人类从真实的数据中辨别。在本文中，我们提出了一种使用GAN生成现实外观的ECG信号的方法。我们利用它们来训练和评估一种可用于ECG信号的最新过滤质量的Denoising AutoCododer。已经证明，与仅在实际数据上训练的模型相比，生成的数据改善了模型性能。我们还通过重复使用训练有素的歧视网络来调查转移学习的效果。
Generative Adversarial Networks (GAN) are known to produce synthetic data that are difficult to discern from real ones by humans. In this paper we present an approach to use GAN to produce realistically looking ECG signals. We utilize them to train and evaluate a denoising autoencoder that achieves state-of-the-art filtering quality for ECG signals. It is demonstrated that generated data improves the model performance compared to the model trained on real data only. We also investigate an effect of transfer learning by reusing trained discriminator network for denoising model.
