Skip to main content

Table 1 Comparison of TWA detection rate for NMF-Adaptive SM using the proposed fuzzy labeling classifier and LDA

From: Discriminant non-stationary signal features’ clustering using hard and fuzzy cluster labeling

Method Sensitivity (%) Specificity (%) Classifier TWA magnitude (μ V) ECG database
NMF-Adaptive SM 92 95 Fuzzy labeling 5 52 Real ECGs
NMF-adaptive SM 87 91 LDA 5 52 Real ECGs
SM [25] 73 63 LDA 5 52 Real ECGs
MMA [25] 92 58 LDA 5 52 Real ECGs
Wavelet 1 [29] 77 NS Wilcoxon rank-sum test 10 10 Synthetic ECGs
Wavelet 2 [30] 96 NS LDA 10 2050 Synthetic ECGs
  1. The results of two well-known T-wave analysis methods (SM and MMA) and two wavelet-based TWA detection methods are also reported in the table. ‘NS’ indicates ‘Not Specified’.