Department of Engineering, King's College London, London WC2R 2LS, UK.
Faculté de Médecine, Université de Kindu, Kindu, Maniema, Democratic Republic of the Congo.
Sensors (Basel). 2022 Mar 15;22(6):2261. doi: 10.3390/s22062261.
Deep learning techniques are the future trend for designing heart sound classification methods, making conventional heart sound segmentation dispensable. However, despite using fixed signal duration for training, no study has assessed its effect on the final performance in detail. Therefore, this study aims at analysing the duration effect on the commonly used deep learning methods to provide insight for future studies in data processing, classifier, and feature selection. The results of this study revealed that (1) very short heart sound signal duration (1 s) weakens the performance of Recurrent Neural Networks (RNNs), whereas no apparent decrease in the tested Convolutional Neural Network (CNN) model was found. (2) RNN outperformed CNN using Mel-frequency cepstrum coefficients (MFCCs) as features. There was no difference between RNN models (LSTM, BiLSTM, GRU, or BiGRU). (3) Adding dynamic information (∆ and ∆²MFCCs) of the heart sound as a feature did not improve the RNNs' performance, and the improvement on CNN was also minimal (≤2.5% in ). The findings provided a theoretical basis for further heart sound classification using deep learning techniques when selecting the input length.
深度学习技术是设计心音分类方法的未来趋势，使得传统的心音分割变得不必要。然而，尽管在训练中使用固定的信号持续时间，但没有研究详细评估其对最终性能的影响。因此，本研究旨在分析持续时间对常用深度学习方法的影响，为未来在数据处理、分类器和特征选择方面的研究提供参考。本研究的结果表明：（1）心音信号持续时间非常短（1 秒）会削弱递归神经网络（RNN）的性能，而测试的卷积神经网络（CNN）模型没有明显下降。（2）使用梅尔频率倒谱系数（MFCCs）作为特征时，RNN 优于 CNN。RNN 模型（LSTM、BiLSTM、GRU 或 BiGRU）之间没有差异。（3）添加心音的动态信息（∆ 和 ∆²MFCCs）作为特征并没有提高 RNN 的性能，对 CNN 的改进也很小（≤2.5%）。研究结果为进一步使用深度学习技术进行心音分类提供了理论依据，在选择输入长度时具有指导意义。
