Skip to main content

Table 4 Comparison of the F1 measure applied on the spectrogram

From: A novel approach to extracting useful information from noisy TFDs using 2D local entropy measures

SNRProposed methodLocal entropy-based algorithmRICI TFD threshold5%10%15%
Signal 1
−3 dBF1= 0.865F1= 0.778F1= 0.868F1= 0.673F1= 0.785F1= 0.792
0 dBF1= 0.909F1= 0.869F1= 0.896F1= 0.706F1= 0.85F1= 0.872
3 dBF1= 0.873F1= 0.884F1= 0.939F1= 0.936F1= 0.91F1= 0.853
6 dBF1= 0.924F1= 0.887F1= 0.94F1= 0.479F1= 0.479F1= 0.479
10 dBF1= 0.932F1= 0.939F1= 0.918F1= 0.479F1= 0.479F1= 0.479
Signal 2
−3 dBF1= 0.769F1= 0.763F1= 0.768F1= 0.699F1= 0.764F1= 0.742
0 dBF1= 0.864F1= 0.823F1= 0.864F1= 0.772F1= 0.838F1= 0.798
3 dBF1= 0.913F1= 0.793F1 =0.9F1= 0.9F1= 0.829F1= 0.74
6 dBF1= 0.943F1= 0.915F1= 0.93F1= 0.477F1= 0.477F1= 0.477
10 dBF1= 0.959F1= 0.942F1= 0.943F1= 0.477F1= 0.477F1= 0.477