J Wave Autodetection Using Analytic Time-Frequency Flexible Wavelet Transformation Applied on ECG Signals

Table 5

Comparison of proposed method with other existing methods of J wave automatic detection.

Authors	Applied methods	Classification	ACC (%)	SEN (%)	SPE (%)
Clark et al. (2014)	Glasgow ECG analysis program with new logic		91.3	89.5	94.5
Wang et al. (2015)	GE Marquette 12-SL program 2001 version	Functional data analysis	89.6	88.45	87.8
Li et al. (2015)	Time-domain features and discrete wavelet transform (DWT)	Hidden Markov model (HMM)	93.35	91.32	92.2
Li et al. (2015)	Curve fitting and wavelet transform (WT)	SVM	92.58	93.21	93.87
Li et al. (2016)	Time-domain features, power spectrum, and cumulative probability	Decision tree (DT)	96.03	95.1	96.25
In the present work	ATFFWT and Fuzzy Entropy	LS-SVM	97.61	97.76	95.82