Review Reports
- Pengfei Ma1,†,
- Yuesen Liu2 and
- Lin Li2,†
- et al.
Reviewer 1: Asadullah Shaikh Reviewer 2: Kapil Joshi Reviewer 3: Anonymous
Round 1
Reviewer 1 Report
The paper presents an anti-frequency-offset constellation diagram (AFO-CD) extraction method. The proposed solution indicates the change of the CD with time and enables to suppression of the influence of frequency-offset efficiently.
The paper is well written and well organized, however, the entire related work section is missing. I advise authors to add related work along with a clear comparison with the proposed approach and published approaches.
Explain experimental platform further specially Nvidia GeForce RTX 2080Ti GPU. How simulation signals were obtained.
Discuss the limitations of the work.
Add future work in the conclusion section
Author Response
The attached is the response.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Figure 8. Comparison of the recognition accuracy of real measured signal at different frequency offsets when the SNR is -10d --Explain this figure more.
The explanation and significance of graphs must be discussed for better readability. The captions of figures are missing in the article.
use more parameters as in Figure 7 and Figure 8
No references are cited in the text of the article. How authors presented the study without referring to any articles. How they have identified the problem, motivation, and research gap.
well written with proposed methodology.
Latest Reference must be included in this manuscript.
Explain the use of this diagram: Figure 2. The CD sequences of three PSK signal
Author Response
The attached is the response.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper proposes a signal modulation recognition method based on AFO-CD features.
The subject is interesting, there are some original end new elements, such as the AF-RDGNN model used as classifier. The simulations results showed that it has good performance in terms of accuracy for digital communication signals under high frequency-offsets condition.
Compared with other existing methods, the proposed one has higher accuracy performance, which proves its effectiveness.
The proposed method is well described.
The paper is well organized, it technically sounds. The contributions and the results are clearly presented.
Author Response
The attached is the response.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors have addressed most of the comments except
The entire related work section is missing. I advise authors to add related work and a clear comparison between the proposed and published approaches.
It's better to add related work as a separate section.
Kindly mention the line number where the comments are addressed
Author Response
The attached is response. Thanks!
Author Response File: Author Response.pdf
Round 3
Reviewer 1 Report
No further comments