A Meta-Transfer Learning Approach to ECG Arrhythmia Detection
A Meta-Transfer Learning Approach to ECG Arrhythmia Detection
复制标题
DOI：
10.1109/embc48229.2022.9871518
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Wuxiao Chen;T. Banerjee;E. John
中科院分区：
文献类型：
--
作者：
Wuxiao Chen;T. Banerjee;E. John
随着心电记录的普及，心脏异常的自动分类变得越来越流行。许多信号处理和机器学习算法已经显示出准确识别心脏异常的潜力。然而，这些方法中的大多数严重依赖于大量的相对同类的数据集。在现实生活中，可能没有足够的数据用于特定类别，在这种情况下，常规的深度学习可能会失败。一种直截了当的直觉是使用从以前的数据中学到的知识来解决问题。这个想法导致了学习-学习：推断从旧数据集中积累的知识，并将其用于不同但略有关联的数据集中。这样，我们就不需要有大量的数据来学习新的任务，因为新旧数据集的基本特征彼此相似。本文提出了一种新的机器学习方法来解决有限数据量的心电心律失常检测问题。该方法结合了当前流行的元学习和迁移学习技术。实验结果表明，该方法在较少数据的情况下达到了较高的分类准确率，并且学习速度快于常规的深度学习。
Automatic classification of cardiac abnormalities is becoming increasingly popular with the prevalence of ECG recordings. Many signal processing and machine learning algorithms have shown the potential to identify cardiac ab-normalities accurately. However, most of these methods heavily rely on a large amount of relatively homogeneous datasets. In real life, chances are that there is not enough data for a specific category, and regular deep learning may fail in this scenario. A straightforward intuition is to use the knowledge learned from previous data to solve the problem. This idea leads to learning-to-learn: extrapolating the knowledge accumulated from the old dataset and using it in a different but somewhat related dataset. In this way, we do not need to have considerable data to learn the new task because the underlying features of the old and new datasets resemble one another. In this paper, a novel machine learning method is introduced to solve the ECG arrhythmia detection problem with a limited amount of data. The proposed method combines the popular techniques of meta-learning and transfer learning. It is shown that our method achieves much higher accuracy in ECG arrhythmia classification with a few data and learns the new task faster than regular deep learning.