Lightweight End-to-End Neural Network Model for Automatic Heart Sound Classification release_gxi3hzlmpzajrnflhxubzbkxs4

by Tao Li, Yibo Yin, Kainan Ma, Sitao Zhang, Ming Liu

Published in Information by MDPI AG.

2021   Volume 12, p54

Abstract

Heart sounds play an important role in the initial screening of heart diseases. However, the accurate diagnosis with heart sound signals requires doctors to have many years of clinical experience and relevant professional knowledge. In this study, we proposed an end-to-end lightweight neural network model that does not require heart sound segmentation and has very few parameters. We segmented the original heart sound signal and performed a short-time Fourier transform (STFT) to obtain the frequency domain features. These features were sent to the improved two-dimensional convolutional neural network (CNN) model for features learning and classification. Considering the imbalance of positive and negative samples, we introduced FocalLoss as the loss function, verified our network model with multiple random verifications, and, hence, obtained a better classification result. Our main purpose is to design a lightweight network structure that is easy for hardware implementation. Compared with the results of the latest literature, our model only uses 4.29 K parameters, which is 1/10 of the size of the state-of-the-art work.
In application/xml+jats format

Archived Files and Locations

application/pdf  2.6 MB
file_2y7fbv2wf5gexidfqp7gszuvsq
res.mdpi.com (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2021-01-26
Language   en ?
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  2078-2489
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bd2e7d3c-2773-467c-9b1e-5031aa23512f
API URL: JSON