A Cascade Network for Blind Recognition of LDPC Codes

Round 1

Reviewer 1 Report

The paper presents a new method based on deep learning to approach the problem of recognition of low density parity check (LDPC) codes. More specifically, the authors use convolutional neural network (CNN).

Generally, no major technical flaw is found. The CNN method was invented long time ago and has been applied to many different areas. Its application here to the LDPC code recognition seems to be reasonable, too. Simulation results are also convincing.

However, English languages may be improved, e.g., flow of languages and wordings. Publication is recommended upon minor changes.

Author Response

Thanks your decision and constructive comments on our manuscript. We have carefully considered the suggestion and tried our best to improve, and the entire manuscript has been edited by a native English speaker.

Reviewer 2 Report

The authors present a cascade network for blind recognition of LDPC codes. Please consider the following remarks:

1) Please provide more recent references. The majority is until 2019.

2) At section 2.3.2 there are no references. Please specify if figures 2, 3 and equations 8, 9, 10 are novel and are proposed by the authors.

3) Line 330: What "Deployed" means?

4) The english of the paper are poor.

5) Figure 1 is not very clear.

6) Table 5 must be removed. Its content is obvious.

7) At conclusions section there is no mention about LDPC codes. The paper according to its title works on LDPC channel coding. Therefore, the conclusions section is incomplete and must be rewritten.

8) Please give more details about LDPC codes parameters used at simulation results (e.g. parity chech matrix H).

9) Please provide references for section 2.2.

10) What type of simulation tool is used? Please specify.

11) Please provide a more clear explanation for Tables 4 and 6.

12) Line 311: What "EM" represents? Please explain.

13) Please explain if the proposed architecture can be used in current or future systems which use LDPC channel coding (maybe 5G systems?).

14) Please provide ideas on future improvement of the proposed architecture (future work).

Author Response

Thanks your decision and constructive comments on our manuscript. We have carefully considered the suggestion and tried our best to improve. The red part that has been revised according to your comments.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors did modifications to the initial manuscript according to the suggestions. I recommend the article to be published in its present form. One last suggestion is the authors to make a final English check.