Next Article in Journal
3D Digital Adaptive Thorax Modelling of Peoples with Spinal Disabilities: Applications for Performance Clothing Design
Previous Article in Journal
Air Pollution: Sensitive Detection of PM2.5 and PM10 Concentration Using Hyperspectral Imaging
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 11
Issue 10
10.3390/app11104544
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization

by
Yoojin Jeong
,
Juhee Kim
,
Daeyeol Kim
,
Jinsoo Kim
and
Kwangkee Lee
*
Tvstorm, Sunghyun Bldg., Seoul 137875, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2021, 11(10), 4544; https://doi.org/10.3390/app11104544
Submission received: 7 April 2021 / Revised: 27 April 2021 / Accepted: 10 May 2021 / Published: 17 May 2021
(This article belongs to the Section Computing and Artificial Intelligence)
Browse Figures
Versions Notes

Abstract

Cardiac auscultation is a cost-effective and noninvasive technique for cardiovascular disease detection. Recently, various studies have been underway for cardiac auscultation using deep learning, not doctors. When training a deep learning network, it is important to secure large amount of high-quality data. However, medical data are difficult to obtain, and in most cases the number of abnormal classes is insufficient. In this study, data augmentation is used to supplement the insufficient amount of data, and data generalization to generate data suitable for convolutional neural networks (CNN) is proposed. We demonstrate performance improvements by inputting them into the CNN. Our method achieves an overall performance of 96%, 81%, and 90% for sensitivity, specificity, and F1-score, respectively. Diagnostic accuracy was improved by 18% compared to when it was not used. Particularly, it showed excellent detection success rate for abnormal heart sounds. The proposed method is expected to be applied to an automatic diagnosis system to detect heart abnormalities and help prevent heart disease through early detection.
Keywords: cardiovascular disease; heart sounds; heartbeat classification; signal preprocessing; convolutional neural network; deep learning cardiovascular disease; heart sounds; heartbeat classification; signal preprocessing; convolutional neural network; deep learning

Share and Cite

MDPI and ACS Style

Jeong, Y.; Kim, J.; Kim, D.; Kim, J.; Lee, K. Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization. Appl. Sci. 2021, 11, 4544. https://doi.org/10.3390/app11104544

AMA Style

Jeong Y, Kim J, Kim D, Kim J, Lee K. Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization. Applied Sciences. 2021; 11(10):4544. https://doi.org/10.3390/app11104544

Chicago/Turabian Style

Jeong, Yoojin, Juhee Kim, Daeyeol Kim, Jinsoo Kim, and Kwangkee Lee. 2021. "Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization" Applied Sciences 11, no. 10: 4544. https://doi.org/10.3390/app11104544

APA Style

Jeong, Y., Kim, J., Kim, D., Kim, J., & Lee, K. (2021). Methods for Improving Deep Learning-Based Cardiac Auscultation Accuracy: Data Augmentation and Data Generalization. Applied Sciences, 11(10), 4544. https://doi.org/10.3390/app11104544

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop