An Effective ECG Arrhythmia Classification Algorithm

Autor:	Wei-Chun Chiang, Ya-Ting Carolyn Yang, Yu-Liang Hsu, Jeen-Shing Wang
Rok vydání:	2012
Předmět:	Probabilistic neural network Sampling (signal processing) business.industry Speech recognition Principal component analysis Pattern recognition Classification scheme Artificial intelligence Ecg signal business Linear discriminant analysis Classifier (UML) Mathematics
Zdroj:	Bio-Inspired Computing and Applications ISBN: 9783642245527 ICIC (3)
DOI:	10.1007/978-3-642-24553-4_72
Popis:	This paper presents an effective electrocardiogram (ECG) arrhythmia classification scheme consisting of a feature reduction method combining principal component analysis (PCA) with linear discriminant analysis (LDA), and a probabilistic neural network (PNN) classifier to discriminate eight different types of arrhythmia from ECG beats. Each ECG beat sample composed of 200 sampling points at a 360 Hz sampling rate around an R peak is extracted from ECG signals. The feature reduction method is employed to find important features from ECG beats, and to improve the classification accuracy of the classifier. With the features, the PNN is then trained to serve as classifier for discriminating eight different types of ECG beats. The average classification accuracy of the proposed scheme is 99.71%. Our experimental results have successfully validated the integration of the PNN classifier with the proposed feature reduction method can achieve satisfactory classification accuracy.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::91dfd07357760ecf9ed87a3f85f373a1 https://doi.org/10.1007/978-3-642-24553-4_72 Zobrazit plný text záznamu