Machine Learning ECG Classification Using Wavelet Scattering of Feature Extraction

Table 1

Different classifiers have been proposed for arrhythmia discrimination.

Work	Feature extraction	Classifier	Accuracy%
Sultan-Qurraie S and Ghorbani Afkhami R(2017)	Time-frequency, RR-interval, and higher-order statistical	Decision trees	98.92
Iryna Mykoliuk, Daniel Jancarczyk, Mikolaj Karpinski, and Viktor Kifer(2018)	Pan-Tompkins algorithm and RR-intervals	Random forest and neural network	98.6
Ledezma CA, Zhou X, Rodríguez B, Tan PJ, and Díaz-Zuccarini V(2019)	Pseudo-ECG	Neural network	95
S. K. Pandeya, R. R. Janghel, V. Vani(2020)	Morphological, RR-intervals, wavelet transformer, and higher-order statistical	SVM, LSTM, KNN, and random forest	94.4
M. Alfaras, M. C. Soriano and S. Ortín(2019)	R-R intervals	Echo state network	95.7
Md Rafiul Hassan a, Shamsul Huda B, and Mohammad Mehedi Hassan(2022)	Deep learning neural network (DLNN)	Multiclass CAN and deep learning neural network (DLNN)	88.95
Sudestna Nahak and Goutam Saha(2020)	Pan-Tompkins algorithm	Support vector machine (SVM)	93.33
Axel Sepúlved, Francisco Castillo, Carlos Palma, and Maria Rodriguez-Fernandez	Time domain, frequency domain, and wavelet scattering	Linear discriminant analysis (LDA) and decision tree	82.7