Interference Response Prediction of Receiver Based on Wavelet Transform and a Temporal Convolution Network

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Review report is attached

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Minor revision is needed like spaces between words and circular bracket in line 249 rather than a rectangular one.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The authors present a novel approach that integrates wavelet transform with a temporal convolutional network. The model begins with a data pre-processing stage, where wavelet transform decomposes the original signal into various scales. Although the paper in general is well developed, there are some shortcomings that I highlight:

1) Are the equations your authorship? If not, they must be referenced, no equation has a prior reference.

2) the numeral of equation 5 is repeated twice

3) Equations 3, 4 and 5 are not properly derived or expressed in their obtaining, generating an analytical void in the reader.

4) The conclusions do not partially demonstrate the analysis with relevant hard data obtained from the most important results of the work.

5) Why was the R-squared method used and not other evaluation methods?

Comments on the Quality of English Language

English must be reviewed throughout the paper.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In this manuscript, the authors studied the problem of Interference Response Prediction. Specifically, the authors proposed a four-step approach to solve the problem. Firstly, the wavelet transform is employed to decompose interference signals into coefficients at various frequency scales. Secondly, the temporal convolution network model extracts the corresponding features of each frequency component from each layer of coefficients. Thirdly, the stacked Attention Feature Fusion module is used to fuse local and global features across different frequency scales. Finally, the predictor, consisting of fully connected layers, predicts the time-domain signal output of the receiver's video end based on the fused features. Overall, the idea presented in this manuscript is interesting and marginally new. Numerical results have shown that the proposed scheme outperforms some existing methods. However, there are some areas of improvement that the authors may need to incorporate. The presentation is below average, there are numerous grammatical and typo errors that need to be corrected. Also, the authors may want to include some study on complexity analysis and compare those of the state-of-the-art methods.

Comments on the Quality of English Language

The presentation is below average, there are numerous grammatical and typo errors that need to be corrected.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

No Comments

Reviewer 2 Report

Comments and Suggestions for Authors

Changes and improvements made to the paper based on my comments were addressed. The paper can be published.

Comments on the Quality of English Language

 Minor editing of English language required

Reviewer 3 Report

Comments and Suggestions for Authors

The authors have addressed my comments adequately.