Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods

Shaocan  Fan; Boomadevi Sekar; Peng Un Mak; Sio Hang  Pun; Mang I  Vai

doi:10.1142/9789813273238_0183

Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods

Shaocan Fan, Boomadevi Sekar, Peng Un Mak, Sio Hang Pun, Mang I Vai

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

Abstract

Heart sound de-noising is considered as an important signal pre-processing step in developing computer assisted heart auscultation model. In this paper, we investigate three white noise reduction methods, namely wavelet transform, wavelet packet transform, and empirical mode decomposition for heart sound de-noising. The de-noised signals are evaluated using signal-to-noise ratio and root mean square error. The results show wavelet transform and empirical mode decomposition methods outperform the wavelet packet
transform in heart sound de-noising. The wavelet transform method with 'dmey' wavelet provides a better result for most of the heart sound records. These three de-noising methods are useful to attenuate the white Gaussian noise. It can provide a high quality signal for further signal processing and classifying the heart sound signal.

Original language	English
Title of host publication	Data Science and Knowledge Engineering for Sensing Decision Support
Editors	Jun Liu, Jie Lu, Yang Xu, Luis Martinez, Etienne Kerre
Publisher	World Scientific Publishing
Pages	1470-1477
ISBN (Electronic)	978-981-3273-24-5
ISBN (Print)	978-981-3273-22-1
DOIs	https://doi.org/10.1142/9789813273238_0183 https://doi.org/10.1142/11069
Publication status	Published (in print/issue) - 31 Oct 2018
Event	FLINS/ISKE 2018 : FLINS Conference on Data Science and Knowledge Engineering for Sensing Decision Support & ISKE Conference on Systems and Knowledge Engineering - Northern Ireland, Belfast Duration: 21 Aug 2018 → 24 Aug 2018

Publication series

Name	Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science
Publisher	World Scientific
Volume	11
ISSN (Print)	1793-7868

Conference

Conference	FLINS/ISKE 2018 : FLINS Conference on Data Science and Knowledge Engineering for Sensing Decision Support & ISKE Conference on Systems and Knowledge Engineering
City	Belfast
Period	21/08/18 → 24/08/18

Access to Document

Cite this

Fan, S., Sekar, B., Mak, P. U., Pun, S. H., & Vai, M. I. (2018). Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods. In J. Liu, J. Lu, Y. Xu, L. Martinez, & E. Kerre (Eds.), Data Science and Knowledge Engineering for Sensing Decision Support (pp. 1470-1477). ( Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science; Vol. 11). World Scientific Publishing. https://doi.org/10.1142/9789813273238_0183, https://doi.org/10.1142/11069

Fan, Shaocan ; Sekar, Boomadevi ; Mak, Peng Un et al. / Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods. Data Science and Knowledge Engineering for Sensing Decision Support. editor / Jun Liu ; Jie Lu ; Yang Xu ; Luis Martinez ; Etienne Kerre. World Scientific Publishing, 2018. pp. 1470-1477 ( Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science).

@inproceedings{1cbce1b31fe5463b9a7b8cd3e8e5e1a6,

title = "Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods",

abstract = "Heart sound de-noising is considered as an important signal pre-processing step in developing computer assisted heart auscultation model. In this paper, we investigate three white noise reduction methods, namely wavelet transform, wavelet packet transform, and empirical mode decomposition for heart sound de-noising. The de-noised signals are evaluated using signal-to-noise ratio and root mean square error. The results show wavelet transform and empirical mode decomposition methods outperform the wavelet packet transform in heart sound de-noising. The wavelet transform method with 'dmey' wavelet provides a better result for most of the heart sound records. These three de-noising methods are useful to attenuate the white Gaussian noise. It can provide a high quality signal for further signal processing and classifying the heart sound signal. ",

author = "Shaocan Fan and Boomadevi Sekar and Mak, {Peng Un} and Pun, {Sio Hang} and Vai, {Mang I}",

year = "2018",

month = oct,

day = "31",

doi = "10.1142/9789813273238_0183",

language = "English",

isbn = "978-981-3273-22-1",

series = " Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science",

publisher = "World Scientific Publishing",

pages = "1470--1477",

editor = "Jun Liu and Jie Lu and Yang Xu and Luis Martinez and Etienne Kerre",

booktitle = "Data Science and Knowledge Engineering for Sensing Decision Support",

address = "Singapore",

note = "FLINS/ISKE 2018 : FLINS Conference on Data Science and Knowledge Engineering for Sensing Decision Support & ISKE Conference on Systems and Knowledge Engineering ; Conference date: 21-08-2018 Through 24-08-2018",

}

Fan, S, Sekar, B, Mak, PU, Pun, SH & Vai, MI 2018, Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods. in J Liu, J Lu, Y Xu, L Martinez & E Kerre (eds), Data Science and Knowledge Engineering for Sensing Decision Support. Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science, vol. 11, World Scientific Publishing, pp. 1470-1477, FLINS/ISKE 2018 : FLINS Conference on Data Science and Knowledge Engineering for Sensing Decision Support & ISKE Conference on Systems and Knowledge Engineering , Belfast, 21/08/18. https://doi.org/10.1142/9789813273238_0183, https://doi.org/10.1142/11069

Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods. / Fan, Shaocan ; Sekar, Boomadevi; Mak, Peng Un et al.
Data Science and Knowledge Engineering for Sensing Decision Support. ed. / Jun Liu; Jie Lu; Yang Xu; Luis Martinez; Etienne Kerre. World Scientific Publishing, 2018. p. 1470-1477 ( Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science; Vol. 11).

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

TY - GEN

T1 - Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods

AU - Fan, Shaocan

AU - Sekar, Boomadevi

AU - Mak, Peng Un

AU - Pun, Sio Hang

AU - Vai, Mang I

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Heart sound de-noising is considered as an important signal pre-processing step in developing computer assisted heart auscultation model. In this paper, we investigate three white noise reduction methods, namely wavelet transform, wavelet packet transform, and empirical mode decomposition for heart sound de-noising. The de-noised signals are evaluated using signal-to-noise ratio and root mean square error. The results show wavelet transform and empirical mode decomposition methods outperform the wavelet packet transform in heart sound de-noising. The wavelet transform method with 'dmey' wavelet provides a better result for most of the heart sound records. These three de-noising methods are useful to attenuate the white Gaussian noise. It can provide a high quality signal for further signal processing and classifying the heart sound signal.

AB - Heart sound de-noising is considered as an important signal pre-processing step in developing computer assisted heart auscultation model. In this paper, we investigate three white noise reduction methods, namely wavelet transform, wavelet packet transform, and empirical mode decomposition for heart sound de-noising. The de-noised signals are evaluated using signal-to-noise ratio and root mean square error. The results show wavelet transform and empirical mode decomposition methods outperform the wavelet packet transform in heart sound de-noising. The wavelet transform method with 'dmey' wavelet provides a better result for most of the heart sound records. These three de-noising methods are useful to attenuate the white Gaussian noise. It can provide a high quality signal for further signal processing and classifying the heart sound signal.

UR - https://www.worldscientific.com/series/wspsceis

U2 - 10.1142/9789813273238_0183

DO - 10.1142/9789813273238_0183

M3 - Conference contribution

SN - 978-981-3273-22-1

T3 - Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science

SP - 1470

EP - 1477

BT - Data Science and Knowledge Engineering for Sensing Decision Support

A2 - Liu, Jun

A2 - Lu, Jie

A2 - Xu, Yang

A2 - Martinez, Luis

A2 - Kerre, Etienne

PB - World Scientific Publishing

T2 - FLINS/ISKE 2018 : FLINS Conference on Data Science and Knowledge Engineering for Sensing Decision Support & ISKE Conference on Systems and Knowledge Engineering

Y2 - 21 August 2018 through 24 August 2018

ER -

Fan S, Sekar B, Mak PU, Pun SH, Vai MI. Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods. In Liu J, Lu J, Xu Y, Martinez L, Kerre E, editors, Data Science and Knowledge Engineering for Sensing Decision Support. World Scientific Publishing. 2018. p. 1470-1477. ( Book Series: World Scientific Proceedings Series on Computer Engineering and Information Science). doi: 10.1142/9789813273238_0183, 10.1142/11069

Heart Sound De-noising using Wavelet and Empirical mode Decomposition based Thresholding methods

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this