Skip to main content

Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 4 Classification accuracy of each modulation type (SNRte=SNRtr)

From: A robust modulation classification method using convolutional neural networks

Type M-ASK M-FSK M-PSK M-QAM OFDM LFM MSK Total
SNRte 2 4 8 2 4 8 2 4 8 4 16 64     
− 10 0.950 0.553 0.650 1.0 1.0 0.997 1.0 0.956 0.907 0.999 0.726 0.802 0.985 1.0 1.0 0.9017
− 8 0.979 0.579 0.670 1.0 1.0 0.997 1.0 0.997 0.953 1.0 0.845 0.848 1.0 1.0 1.0 0.9245
− 6 0.997 0.632 0.712 1.0 1.0 0.999 1.0 0.998 0.991 1.0 0.939 0.886 1.0 1.0 1.0 0.9436
− 4 1.0 0.762 0.791 1.0 1.0 1.0 1.0 1.0 0.993 1.0 0.98 0.957 1.0 1.0 1.0 0.9653
− 2 1.0 0.881 0.917 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 0.990 1.0 1.0 1.0 0.9859
0 1.0 0.972 0.972 1.0 1.0 1.0 1.0 0.999 1.0 1.0 1.0 1.0 1.0 1.0 1.0 0.9962
2 1.0 0.992 0.985 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 0.9984
5 1.0 1.0 0.997 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 0.9998
10 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0
15 1.0 1.0 0.998 1.0 1.0 0.999 1.0 1.0 0.999 1.0 1.0 1.0 1.0 0.996 1.0 0.9995
20 1.0 1.0 0.999 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 0.996 1.0 0.9999