ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier

Dapeng FU; Zhourui XIA; Pengfei GAO; Haiqing WANG; Jianping LIN; Li SUN

doi:10.1587/transinf.2017EDP7410

ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier

Dapeng FU, Zhourui XIA, Pengfei GAO, Haiqing WANG, Jianping LIN, Li SUN

Full Text Views

0

Cite this

Summary :

Objective: Detection of Electrocardiogram (ECG) characteristic points can provide critical diagnostic information about heart diseases. We proposed a novel feature extraction and machine learning scheme for automatic detection of ECG characteristic points. Methods: A new feature, termed as randomly selected wavelet transform (RSWT) feature, was devised to represent ECG characteristic points. A random forest classifier was adapted to infer the characteristic points position with high sensitivity and precision. Results: Compared with other state-of-the-art algorithms' testing results on QT database, our detection results of RSWT scheme showed comparable performance (similar sensitivity, precision, and detection error for each characteristic point). RSWT testing on MIT-BIH database also demonstrated promising cross-database performance. Conclusion: A novel RSWT feature and a new detection scheme was fabricated for ECG characteristic points. The RSWT demonstrated a robust and trustworthy feature for representing ECG morphologies. Significance: With the effectiveness of the proposed RSWT feature we presented a novel machine learning based scheme to automatically detect all types of ECG characteristic points at a time. Furthermore, it showed that our algorithm achieved better performance than other reported machine learning based methods.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.8 pp.2082-2091

Publication Date: 2018/08/01

Publicized: 2018/05/09

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7410

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Dapeng FU
  Chinese Academy of Sciences Zhong Guan Cun Hospital
Zhourui XIA
  Beijing University of Posts and Telecommunications
Pengfei GAO
  Tsinghua University
Haiqing WANG
  Beijing Zhong Guan Cun Hospital, Chinese Academy of Sciences Zhong Guan Cun Hospital
Jianping LIN
  Beijing XinHeYiDian Technology Co. Ltd.
Li SUN
  Beijing XinHeYiDian Technology Co. Ltd.

Keyword

ECG, random forest, wavelet transform

Cite this

Copy

Dapeng FU, Zhourui XIA, Pengfei GAO, Haiqing WANG, Jianping LIN, Li SUN, "ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 8, pp. 2082-2091, August 2018, doi: 10.1587/transinf.2017EDP7410.
Abstract: Objective: Detection of Electrocardiogram (ECG) characteristic points can provide critical diagnostic information about heart diseases. We proposed a novel feature extraction and machine learning scheme for automatic detection of ECG characteristic points. Methods: A new feature, termed as randomly selected wavelet transform (RSWT) feature, was devised to represent ECG characteristic points. A random forest classifier was adapted to infer the characteristic points position with high sensitivity and precision. Results: Compared with other state-of-the-art algorithms' testing results on QT database, our detection results of RSWT scheme showed comparable performance (similar sensitivity, precision, and detection error for each characteristic point). RSWT testing on MIT-BIH database also demonstrated promising cross-database performance. Conclusion: A novel RSWT feature and a new detection scheme was fabricated for ECG characteristic points. The RSWT demonstrated a robust and trustworthy feature for representing ECG morphologies. Significance: With the effectiveness of the proposed RSWT feature we presented a novel machine learning based scheme to automatically detect all types of ECG characteristic points at a time. Furthermore, it showed that our algorithm achieved better performance than other reported machine learning based methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7410/_p

Copy

@ARTICLE{e101-d_8_2082,
author={Dapeng FU, Zhourui XIA, Pengfei GAO, Haiqing WANG, Jianping LIN, Li SUN, },
journal={IEICE TRANSACTIONS on Information},
title={ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier},
year={2018},
volume={E101-D},
number={8},
pages={2082-2091},
abstract={Objective: Detection of Electrocardiogram (ECG) characteristic points can provide critical diagnostic information about heart diseases. We proposed a novel feature extraction and machine learning scheme for automatic detection of ECG characteristic points. Methods: A new feature, termed as randomly selected wavelet transform (RSWT) feature, was devised to represent ECG characteristic points. A random forest classifier was adapted to infer the characteristic points position with high sensitivity and precision. Results: Compared with other state-of-the-art algorithms' testing results on QT database, our detection results of RSWT scheme showed comparable performance (similar sensitivity, precision, and detection error for each characteristic point). RSWT testing on MIT-BIH database also demonstrated promising cross-database performance. Conclusion: A novel RSWT feature and a new detection scheme was fabricated for ECG characteristic points. The RSWT demonstrated a robust and trustworthy feature for representing ECG morphologies. Significance: With the effectiveness of the proposed RSWT feature we presented a novel machine learning based scheme to automatically detect all types of ECG characteristic points at a time. Furthermore, it showed that our algorithm achieved better performance than other reported machine learning based methods.},
keywords={},
doi={10.1587/transinf.2017EDP7410},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier
T2 - IEICE TRANSACTIONS on Information
SP - 2082
EP - 2091
AU - Dapeng FU
AU - Zhourui XIA
AU - Pengfei GAO
AU - Haiqing WANG
AU - Jianping LIN
AU - Li SUN
PY - 2018
DO - 10.1587/transinf.2017EDP7410
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2018
AB - Objective: Detection of Electrocardiogram (ECG) characteristic points can provide critical diagnostic information about heart diseases. We proposed a novel feature extraction and machine learning scheme for automatic detection of ECG characteristic points. Methods: A new feature, termed as randomly selected wavelet transform (RSWT) feature, was devised to represent ECG characteristic points. A random forest classifier was adapted to infer the characteristic points position with high sensitivity and precision. Results: Compared with other state-of-the-art algorithms' testing results on QT database, our detection results of RSWT scheme showed comparable performance (similar sensitivity, precision, and detection error for each characteristic point). RSWT testing on MIT-BIH database also demonstrated promising cross-database performance. Conclusion: A novel RSWT feature and a new detection scheme was fabricated for ECG characteristic points. The RSWT demonstrated a robust and trustworthy feature for representing ECG morphologies. Significance: With the effectiveness of the proposed RSWT feature we presented a novel machine learning based scheme to automatically detect all types of ECG characteristic points at a time. Furthermore, it showed that our algorithm achieved better performance than other reported machine learning based methods.
ER -