ECG arrhythmia classification using a probabilistic neural network with a feature reduction method
作者： Jeen-Shing Wang , Wei-Chun Chiang , Yu-Liang Hsu , Ya-Ting C. Yang
DOI: 10.1016/J.NEUCOM.2011.10.045
关键词: Linear discriminant analysis 、 Ecg signal 、 Classification scheme 、 Pattern recognition 、 Principal component analysis 、 Probabilistic neural network 、 Classifier (UML) 、 Mathematics 、 Artificial intelligence 、 Sampling (signal processing)
摘要: Abstract This paper presents an effective electrocardiogram (ECG) arrhythmia classification scheme consisting of a feature reduction method combining principal component analysis (PCA) with linear discriminant (LDA), and probabilistic neural network (PNN) classifier to discriminate eight different types from ECG beats. Each beat sample composed 200 sampling points at 360 Hz rate around R peak is extracted signals. The employed find important features beats, improve the accuracy classifier. With selected features, PNN then trained serve as for discriminating average proposed 99.71%. Our experimental results have successfully validated that integration can achieve satisfactory accuracy.
elsevier.com
sci-hub.se 参考文章(32)
Yüksel Özbay, Gülay Tezel, A new method for classification of ECG arrhythmias using neural network with adaptive activation function Digital Signal Processing. ,vol. 20, pp. 1040- 1049 ,(2010) , 10.1016/J.DSP.2009.10.016
Donald F. Specht, Probabilistic neural networks Neural Networks. ,vol. 3, pp. 109- 118 ,(1990) , 10.1016/0893-6080(90)90049-Q
Mehmet Korürek, Ali Nizam, Clustering MIT--BIH arrhythmias with Ant Colony Optimization using time domain and PCA compressed wavelet coefficients Digital Signal Processing. ,vol. 20, pp. 1050- 1060 ,(2010) , 10.1016/J.DSP.2009.10.019
İnan Güler, Elif Derya Übeylı˙, ECG beat classifier designed by combined neural network model Pattern Recognition. ,vol. 38, pp. 199- 208 ,(2005) , 10.1016/J.PATCOG.2004.06.009
Rahime Ceylan, Yüksel Özbay, Bekir Karlik, A novel approach for classification of ECG arrhythmias: Type-2 fuzzy clustering neural network Expert Systems With Applications. ,vol. 36, pp. 6721- 6726 ,(2009) , 10.1016/J.ESWA.2008.08.028
De-Shuang Huang, The united adaptive learning algorithm for the link weights and shape parameter in RBFN for pattern recognition International Journal of Pattern Recognition and Artificial Intelligence. ,vol. 11, pp. 873- 888 ,(1997) , 10.1142/S0218001497000391
Yun-Chi Yeh, Wen-June Wang, Che Wun Chiou, Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals Measurement. ,vol. 42, pp. 778- 789 ,(2009) , 10.1016/J.MEASUREMENT.2009.01.004
Francisco Castells, Pablo Laguna, Leif Sörnmo, Andreas Bollmann, José Millet Roig, Principal component analysis in ECG signal processing EURASIP Journal on Advances in Signal Processing. ,vol. 2007, pp. 98- 98 ,(2007) , 10.1155/2007/74580
Kemal Polat, Salih Güneş, Detection of ECG Arrhythmia using a differential expert system approach based on principal component analysis and least square support vector machine Applied Mathematics and Computation. ,vol. 186, pp. 898- 906 ,(2007) , 10.1016/J.AMC.2006.08.020
S YU, K CHOU, Integration of independent component analysis and neural networks for ECG beat classification Expert Systems With Applications. ,vol. 34, pp. 2841- 2846 ,(2008) , 10.1016/J.ESWA.2007.05.006