Novel ECG Signal Classification Based on KICA Nonlinear Feature Extraction
作者： Hongqiang Li , Huan Liang , Chunjiao Miao , Lu Cao , Xiuli Feng
DOI: 10.1007/S00034-015-0108-3
关键词: Feature extraction 、 Principal component analysis 、 Feature (computer vision) 、 Sampling (signal processing) 、 Artificial intelligence 、 Signal 、 Pattern recognition 、 Data mining 、 Genetic algorithm 、 Computer science 、 Feature vector 、 Support vector machine
摘要: Electrocardiogram (ECG) signal feature extraction is important in diagnosing cardiovascular diseases. This paper presents a new method for nonlinear of ECG signals by combining principal component analysis (PCA) and kernel independent (KICA). The proposed first uses PCA to decrease the dimensions training set then employs KICA calculate space extracting features. Support vector machine (SVM) utilized determine features classification. Genetic algorithm also used optimize SVM parameters. advantageous because it does not require huge amount sampling data, this technique better than traditional strategies select optimal multi-domain space. Computer simulations reveal that yields more satisfactory classification results on MIT---BIH arrhythmia database, reaching an overall accuracy 97.78 %.
springer.com
sci-hub.se 参考文章(21)
V. N. Vapnik, The Nature of Statistical Learning Theory. ,(1995)
Hongqiang Li, Xiaofei Wang, Lei Chen, Enbang Li, Denoising and R-Peak Detection of Electrocardiogram Signal Based on EMD and Improved Approximate Envelope Circuits Systems and Signal Processing. ,vol. 33, pp. 1261- 1276 ,(2014) , 10.1007/S00034-013-9691-3
Hongqiang Li, Xiaofei Wang, Detection of electrocardiogram characteristic points using lifting wavelet transform and Hilbert transform Transactions of the Institute of Measurement and Control. ,vol. 35, pp. 574- 582 ,(2013) , 10.1177/0142331212460720
Can Ye, B. V. K. Vijaya Kumar, M. T. Coimbra, Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals IEEE Transactions on Biomedical Engineering. ,vol. 59, pp. 2930- 2941 ,(2012) , 10.1109/TBME.2012.2213253
Maya Kallas, Clovis Francis, Lara Kanaan, Dalia Merheb, Paul Honeine, Hassan Amoud, Multi-class SVM classification combined with kernel PCA feature extraction of ECG signals international conference on telecommunications. pp. 1- 5 ,(2012) , 10.1109/ICTEL.2012.6221261
Abdelhamid Daamouche, Latifa Hamami, Naif Alajlan, Farid Melgani, A wavelet optimization approach for ECG signal classification Biomedical Signal Processing and Control. ,vol. 7, pp. 342- 349 ,(2012) , 10.1016/J.BSPC.2011.07.001
Saibal Dutta, Amitava Chatterjee, Sugata Munshi, Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification Medical Engineering & Physics. ,vol. 32, pp. 1161- 1169 ,(2010) , 10.1016/J.MEDENGPHY.2010.08.007
Mohamed Cherif Nait-Hamoud, Abdelouaheb Moussaoui, Two novel methods for multiclass ECG arrhythmias classification based on PCA, fuzzy support vector machine and unbalanced clustering 2010 International Conference on Machine and Web Intelligence. pp. 140- 145 ,(2010) , 10.1109/ICMWI.2010.5647931
A. Khazaee, A. Ebrahimzadeh, Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features Biomedical Signal Processing and Control. ,vol. 5, pp. 252- 263 ,(2010) , 10.1016/J.BSPC.2010.07.006
Ataollah Ebrahim Zadeh, Ali Khazaee, Vahid Ranaee, Classification of the electrocardiogram signals using supervised classifiers and efficient features Computer Methods and Programs in Biomedicine. ,vol. 99, pp. 179- 194 ,(2010) , 10.1016/J.CMPB.2010.04.013