Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier

被引:115
作者
Rajesh, Kandala N. V. P. S. [1 ]
Dhuli, Ravindra [1 ]
机构
[1] VIT Univ, Sch Elect Engn, Vellore 632014, Tamil Nadu, India
关键词
ECG signal; Higher order statistics; Class imbalance; Classification; EMPIRICAL MODE DECOMPOSITION; VENTRICULAR-FIBRILLATION; FEATURE-SELECTION; TIME-SERIES; ARRHYTHMIA RECOGNITION; FEATURES; EMD; DISCRIMINATION; MORPHOLOGY; ENTROPY;
D O I
10.1016/j.bspc.2017.12.004
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Computer-aided heartbeat classification has a significant role in the diagnosis of cardiac dysfunction. Electrocardiogram (ECG) provides vital information about the heartbeats. In this work, we propose a method for classifying five groups of heartbeats recommended by AAMI standard EC57:1998. Considering the nature of ECG signal, we employed a non-stationary and nonlinear decomposition technique termed as improved complete ensemble empirical mode decomposition (ICEEMD). Later, higher order statistics and sample entropy measures are computed from the intrinsic mode functions (IMFs) obtained from ICEEMD on each ECG segment. Furthermore, three data level pre-processing techniques are performed on the extracted feature set, to balance the distribution of heartbeat classes. Finally, these features fed to AdaBoost ensemble classifier for discriminating the heartbeats. Simulation results show that the proposed method provides a better solution to the class imbalance problem in heartbeat classification. (C) 2017 Elsevier Ltd. All rights reserved.
引用
收藏
页码:242 / 254
页数:13
相关论文
共 72 条
[1]  
Abeysekera R. M. S. S., 1989, ICASSP-89: 1989 International Conference on Acoustics, Speech and Signal Processing (IEEE Cat. No.89CH2673-2), P1524, DOI 10.1109/ICASSP.1989.266731
[2]   Exploiting correlation of ECG with certain EMD functions for discrimination of ventricular fibrillation [J].
Abu Anas, Emran Mohammad ;
Lee, Soo Yeol ;
Hasan, Md Kamrul .
COMPUTERS IN BIOLOGY AND MEDICINE, 2011, 41 (02) :110-114
[3]   Linear and nonlinear analysis of normal and CAD-affected heart rate signals [J].
Acharya, U. Rajendra ;
Faust, Oliver ;
Sree, Vinitha ;
Swapna, G. ;
Martis, Roshan Joy ;
Kadri, Nahrizul Adib ;
Suri, Jasjit S. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2014, 113 (01) :55-68
[4]   Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals [J].
Afkhami, Rashid Ghorbani ;
Azarnia, Ghanbar ;
Tinati, Mohammad Ali .
PATTERN RECOGNITION LETTERS, 2016, 70 :45-51
[5]   ECG beat detection using filter banks [J].
Afonso, VX ;
Tompkins, WJ ;
Nguyen, TQ ;
Luo, S .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1999, 46 (02) :192-202
[6]   DETECTING VENTRICULAR-FIBRILLATION - SELECTING THE APPROPRIATE TIME-FREQUENCY ANALYSIS TOOL FOR THE APPLICATION [J].
AFONSO, VX ;
TOMPKINS, WJ .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 1995, 14 (02) :152-159
[7]   Wavelet applications in medicine [J].
Akay, M .
IEEE SPECTRUM, 1997, 34 (05) :50-56
[8]   A new adaptive scheme for ECG enhancement [J].
Almenar, V ;
Albiol, A .
SIGNAL PROCESSING, 1999, 75 (03) :253-263
[9]   Reliability of old and new ventricular fibrillation detection algorithms for automated external defibrillators [J].
Amann, Anton ;
Tratnig, Robert ;
Unterkofler, Karl .
BIOMEDICAL ENGINEERING ONLINE, 2005, 4 (1)
[10]  
[Anonymous], 1998, Higher-order spectral analysis toolbox. For use with MATLAB user's guide