Deep Wavelets for Heart Sound Classification

Kun Qian; Zhao Ren; Fengquan Dong; Wen Hsing Lai; Bjorn W. Schuller; Yoshiharu Yamamoto

doi:10.1109/ISPACS48206.2019.8986277

Deep Wavelets for Heart Sound Classification

Kun Qian
, Zhao Ren
, Fengquan Dong
, Wen Hsing Lai
, Bjorn W. Schuller
, Yoshiharu Yamamoto

University of Tokyo
University Hospital Augsburg
Shenzhen University General Hospital
National Kaohsiung University of Applied Sciences
Imperial College London

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

Cardiovascular diseases have a high morbidity, and remain the leading cause of mortality. In the past two decades, developing an intelligent auscultation system has attracted tremendous efforts from the field of signal processing and machine learning. We propose a novel framework based on wavelet representations and deep recurrent neural networks for recognising three heart sounds, i. e., normal, mild, and severe. The Heart Sounds Shenzhen corpus (n = 170) is used to validate the proposed method. The experimental results demonstrate the efficacy of the proposed method in a rigorous subject independent scenario, which can reach an unweighted average recall at 43.0 % (chance level: 33.3%).

Original language	English
Title of host publication	Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728130385
DOIs	https://doi.org/10.1109/ISPACS48206.2019.8986277
State	Published - Dec 2019
Externally published	Yes
Event	2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019 - Taipei, Taiwan, Province of China Duration: 3 Dec 2019 → 6 Dec 2019

Publication series

Name	Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019

Conference

Conference	2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	3/12/19 → 6/12/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Cardiology
Deep Learning
Healthcare
Heart Sound
Wavelets

Access to Document

10.1109/ISPACS48206.2019.8986277

Cite this

Qian, K., Ren, Z., Dong, F., Lai, W. H., Schuller, B. W., & Yamamoto, Y. (2019). Deep Wavelets for Heart Sound Classification. In Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019 Article 8986277 (Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISPACS48206.2019.8986277

Qian, Kun ; Ren, Zhao ; Dong, Fengquan et al. / Deep Wavelets for Heart Sound Classification. Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019).

@inproceedings{57eabca14d5b458f8ef73efd7072a78a,

title = "Deep Wavelets for Heart Sound Classification",

abstract = "Cardiovascular diseases have a high morbidity, and remain the leading cause of mortality. In the past two decades, developing an intelligent auscultation system has attracted tremendous efforts from the field of signal processing and machine learning. We propose a novel framework based on wavelet representations and deep recurrent neural networks for recognising three heart sounds, i. e., normal, mild, and severe. The Heart Sounds Shenzhen corpus (n = 170) is used to validate the proposed method. The experimental results demonstrate the efficacy of the proposed method in a rigorous subject independent scenario, which can reach an unweighted average recall at 43.0 \% (chance level: 33.3\%).",

keywords = "Cardiology, Deep Learning, Healthcare, Heart Sound, Wavelets",

author = "Kun Qian and Zhao Ren and Fengquan Dong and Lai, \{Wen Hsing\} and Schuller, \{Bjorn W.\} and Yoshiharu Yamamoto",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019 ; Conference date: 03-12-2019 Through 06-12-2019",

year = "2019",

month = dec,

doi = "10.1109/ISPACS48206.2019.8986277",

language = "English",

series = "Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019",

}

Qian, K, Ren, Z, Dong, F, Lai, WH, Schuller, BW & Yamamoto, Y 2019, Deep Wavelets for Heart Sound Classification. in Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019., 8986277, Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019, Institute of Electrical and Electronics Engineers Inc., 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019, Taipei, Taiwan, Province of China, 3/12/19. https://doi.org/10.1109/ISPACS48206.2019.8986277

Deep Wavelets for Heart Sound Classification. / Qian, Kun; Ren, Zhao; Dong, Fengquan et al.
Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8986277 (Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Wavelets for Heart Sound Classification

AU - Qian, Kun

AU - Ren, Zhao

AU - Dong, Fengquan

AU - Lai, Wen Hsing

AU - Schuller, Bjorn W.

AU - Yamamoto, Yoshiharu

PY - 2019/12

Y1 - 2019/12

N2 - Cardiovascular diseases have a high morbidity, and remain the leading cause of mortality. In the past two decades, developing an intelligent auscultation system has attracted tremendous efforts from the field of signal processing and machine learning. We propose a novel framework based on wavelet representations and deep recurrent neural networks for recognising three heart sounds, i. e., normal, mild, and severe. The Heart Sounds Shenzhen corpus (n = 170) is used to validate the proposed method. The experimental results demonstrate the efficacy of the proposed method in a rigorous subject independent scenario, which can reach an unweighted average recall at 43.0 % (chance level: 33.3%).

AB - Cardiovascular diseases have a high morbidity, and remain the leading cause of mortality. In the past two decades, developing an intelligent auscultation system has attracted tremendous efforts from the field of signal processing and machine learning. We propose a novel framework based on wavelet representations and deep recurrent neural networks for recognising three heart sounds, i. e., normal, mild, and severe. The Heart Sounds Shenzhen corpus (n = 170) is used to validate the proposed method. The experimental results demonstrate the efficacy of the proposed method in a rigorous subject independent scenario, which can reach an unweighted average recall at 43.0 % (chance level: 33.3%).

KW - Cardiology

KW - Deep Learning

KW - Healthcare

KW - Heart Sound

KW - Wavelets

UR - https://www.scopus.com/pages/publications/85081081670

U2 - 10.1109/ISPACS48206.2019.8986277

DO - 10.1109/ISPACS48206.2019.8986277

M3 - Conference contribution

AN - SCOPUS:85081081670

T3 - Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019

BT - Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019

Y2 - 3 December 2019 through 6 December 2019

ER -

Qian K, Ren Z, Dong F, Lai WH, Schuller BW, Yamamoto Y. Deep Wavelets for Heart Sound Classification. In Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8986277. (Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019). doi: 10.1109/ISPACS48206.2019.8986277

Deep Wavelets for Heart Sound Classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this