Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification

Abstract Automatic feature extraction and classification are two main tasks in abnormal ECG beat recognition. Feature extraction is an important prerequisite prior to classification since it provides the classifier with input features, and the performance of classifier depends significantly on the q...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qin Qin, Jianqing Li, Li Zhang, Yinggao Yue, Chengyu Liu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/dc09429219eb4a87add9ae822818ce61
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dc09429219eb4a87add9ae822818ce61
record_format	dspace
spelling	oai:doaj.org-article:dc09429219eb4a87add9ae822818ce612021-12-02T12:32:01ZCombining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification10.1038/s41598-017-06596-z2045-2322https://doaj.org/article/dc09429219eb4a87add9ae822818ce612017-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-06596-zhttps://doaj.org/toc/2045-2322Abstract Automatic feature extraction and classification are two main tasks in abnormal ECG beat recognition. Feature extraction is an important prerequisite prior to classification since it provides the classifier with input features, and the performance of classifier depends significantly on the quality of these features. This study develops an effective method to extract low-dimensional ECG beat feature vectors. It employs wavelet multi-resolution analysis to extract time-frequency domain features and then applies principle component analysis to reduce the dimension of the feature vector. In classification, 12-element feature vectors characterizing six types of beats are used as inputs for one-versus-one support vector machine, which is conducted in form of 10-fold cross validation with beat-based and record-based training schemes. Tested upon a total of 107049 beats from MIT-BIH arrhythmia database, our method has achieved average sensitivity, specificity and accuracy of 99.09%, 99.82% and 99.70%, respectively, using the beat-based training scheme, and 44.40%, 88.88% and 81.47%, respectively, using the record-based training scheme.Qin QinJianqing LiLi ZhangYinggao YueChengyu LiuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Qin Qin Jianqing Li Li Zhang Yinggao Yue Chengyu Liu Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
description	Abstract Automatic feature extraction and classification are two main tasks in abnormal ECG beat recognition. Feature extraction is an important prerequisite prior to classification since it provides the classifier with input features, and the performance of classifier depends significantly on the quality of these features. This study develops an effective method to extract low-dimensional ECG beat feature vectors. It employs wavelet multi-resolution analysis to extract time-frequency domain features and then applies principle component analysis to reduce the dimension of the feature vector. In classification, 12-element feature vectors characterizing six types of beats are used as inputs for one-versus-one support vector machine, which is conducted in form of 10-fold cross validation with beat-based and record-based training schemes. Tested upon a total of 107049 beats from MIT-BIH arrhythmia database, our method has achieved average sensitivity, specificity and accuracy of 99.09%, 99.82% and 99.70%, respectively, using the beat-based training scheme, and 44.40%, 88.88% and 81.47%, respectively, using the record-based training scheme.
format	article
author	Qin Qin Jianqing Li Li Zhang Yinggao Yue Chengyu Liu
author_facet	Qin Qin Jianqing Li Li Zhang Yinggao Yue Chengyu Liu
author_sort	Qin Qin
title	Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
title_short	Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
title_full	Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
title_fullStr	Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
title_full_unstemmed	Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification
title_sort	combining low-dimensional wavelet features and support vector machine for arrhythmia beat classification
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/dc09429219eb4a87add9ae822818ce61
work_keys_str_mv	AT qinqin combininglowdimensionalwaveletfeaturesandsupportvectormachineforarrhythmiabeatclassification AT jianqingli combininglowdimensionalwaveletfeaturesandsupportvectormachineforarrhythmiabeatclassification AT lizhang combininglowdimensionalwaveletfeaturesandsupportvectormachineforarrhythmiabeatclassification AT yinggaoyue combininglowdimensionalwaveletfeaturesandsupportvectormachineforarrhythmiabeatclassification AT chengyuliu combininglowdimensionalwaveletfeaturesandsupportvectormachineforarrhythmiabeatclassification
_version_	1718394247562919936

Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification

Ejemplares similares