Skip to main content
. 2020 Sep 8;20(18):5112. doi: 10.3390/s20185112

Table 14.

Recall scores of the models considered in this work (as a percentage) for noise rejection performance (best values are highlighted in bold).

SNR RNN-WDCNN WDCNN SRDCNN FFT-SVM FFT-MLP
Average 99.79 (± 0.16) 94.09 (± 1.85) 76.30 (± 3.32) 90.92 (± 0.35) 89.84 (± 0.38)
None 100.00 (± 0.00) 100.00 (± 0.01) 100.00 (± 0.00) 99.63 (± 0.08) 99.51 (± 0.10)
10 dB 100.00 (± 0.00) 100.00 (± 0.01) 99.88 (± 0.06) 99.27 (± 0.13) 98.09 (± 0.23)
8 dB 100.00 (± 0.00) 99.99 (± 0.01) 99.67 (± 0.16) 98.68 (± 0.19) 97.91 (± 0.12)
6 dB 100.00 (± 0.00) 99.99 (± 0.02) 98.15 (± 1.59) 98.20 (± 0.31) 97.07 (± 0.32)
4 dB 100.00 (± 0.00) 99.90 (± 0.07) 90.86 (± 5.19) 96.09 (± 0.38) 95.35 (± 0.43)
2 dB 100.00 (± 0.00) 98.82 (± 0.62) 77.59 (± 5.01) 93.88 (± 0.39) 92.92 (± 0.45)
0 dB 99.96 (± 0.06) 93.94 (± 2.77) 60.59 (± 5.91) 87.27 (± 0.53) 84.91 (± 0.74)
−2 dB 99.67 (± 0.25) 84.61 (± 5.01) 37.66 (± 6.05) 77.03 (± 0.60) 76.64 (± 0.55)
−4 dB 98.45 (± 1.13) 69.59 (± 8.11) 22.31 (± 5.90) 68.20 (± 0.49) 66.17 (± 0.44)