Feature extraction and classification of heart sound using 1D convolutional neural networks

Feature extraction and classification of heart sound using 1D convolutional neural networks

Abstract We proposed a one-dimensional convolutional neural network (CNN) model, which divides heart sound signals into normal and abnormal directly independent of ECG. The deep features of heart sounds were extracted by the denoising autoencoder (DAE) algorithm as the input feature of 1D CNN. The e...

Full description

Bibliographic Details
Main Authors: Fen Li, Ming Liu, Yuejin Zhao, Lingqin Kong, Liquan Dong, Xiaohua Liu, Mei Hui
Format: Article
Language:English
Published: SpringerOpen 2019-12-01
Series:EURASIP Journal on Advances in Signal Processing
Subjects:
Auscultation
Convolutional neural networks (CNNs)
Denoising autoencoder
Heart disease risk
Online Access:https://doi.org/10.1186/s13634-019-0651-3

Internet

https://doi.org/10.1186/s13634-019-0651-3

Similar Items