The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Objectif : La détection des points caractéristiques de l'électrocardiogramme (ECG) peut fournir des informations diagnostiques critiques sur les maladies cardiaques. Nous avons proposé un nouveau schéma d'extraction de caractéristiques et d'apprentissage automatique pour la détection automatique des points caractéristiques de l'ECG. Méthodes : Une nouvelle fonctionnalité, appelée fonctionnalité de transformation en ondelettes sélectionnées au hasard (RSWT), a été conçue pour représenter les points caractéristiques de l'ECG. Un classificateur forestier aléatoire a été adapté pour déduire la position des points caractéristiques avec une sensibilité et une précision élevées. Résultats : comparés aux résultats des tests d'autres algorithmes de pointe sur la base de données QT, nos résultats de détection du schéma RSWT ont montré des performances comparables (sensibilité, précision et erreur de détection similaires pour chaque point caractéristique). Les tests RSWT sur la base de données MIT-BIH ont également démontré des performances prometteuses entre bases de données. Conclusion : Une nouvelle fonctionnalité RSWT et un nouveau schéma de détection ont été fabriqués pour les points caractéristiques de l'ECG. Le RSWT a démontré une fonctionnalité robuste et fiable pour représenter les morphologies ECG. Importance : Grâce à l'efficacité de la fonctionnalité RSWT proposée, nous avons présenté un nouveau schéma basé sur l'apprentissage automatique pour détecter automatiquement tous les types de points caractéristiques ECG à la fois. En outre, cela a montré que notre algorithme obtenait de meilleures performances que les autres méthodes basées sur l’apprentissage automatique signalées.
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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
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
Copier
@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},}
Copier
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 -