Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Wireless communication network.

More »

Fig 1 Expand

Fig 2.

Deep CNN architecture for AMC: (a) the overall architecture of DFENet, (b) the structure of DFE Block, (c) the structure of FEN block.

More »

Fig 2 Expand

Table 1.

Comparison of DFENet with existing multi-branch and multiscale architectures.

More »

Table 1 Expand

Table 2.

Detailed architecture of the DFENet-4block model.

More »

Table 2 Expand

Fig 3.

Accuracy model with filter difference.

More »

Fig 3 Expand

Fig 4.

Classification accuracy with different values of signal length.

More »

Fig 4 Expand

Fig 5.

Accuracy performance of DFENet across 26 modulation types under varying SNR conditions.

More »

Fig 5 Expand

Fig 6.

Confusion matrix of 26-modulation classification at +0 dB SNR.

More »

Fig 6 Expand

Fig 7.

Confusion matrix of 26-modulation classification at +10 dB SNR.

More »

Fig 7 Expand

Fig 8.

Output of the first convolutional layer at SNR = +0 dB.

More »

Fig 8 Expand

Fig 9.

Output of the final fully connected layer at SNR = +0 dB.

More »

Fig 9 Expand

Fig 10.

Output of the final fully connected layer at SNR = +10 dB.

More »

Fig 10 Expand

Table 3.

Ablation study on the HisarMod2019 dataset.

More »

Table 3 Expand

Fig 11.

Classification accuracy with different numbers of DFE blocks.

More »

Fig 11 Expand

Fig 12.

Macro averaged Precision, Recall, and F1-score of DFENet.

More »

Fig 12 Expand

Fig 13.

Comparison of the classification accuracy of different single CNN models for HisarMod2019 dataset.

More »

Fig 13 Expand

Table 4.

Complexity and computational time of the models.

More »

Table 4 Expand

Fig 14.

Comparison of the classification accuracy of different single CNN models for RadioMl2018 dataset.

More »

Fig 14 Expand