Next Article in Journal
Decontamination and Ecological Restoration Performance of a Bioretention Cell-Microbial Fuel Cell under Multiple-Antibiotics Stress
Next Article in Special Issue
Generative Adversarial Network-Based Anomaly Detection and Forecasting with Unlabeled Data for 5G Vertical Applications
Previous Article in Journal
Numerical Study on the Sagging Damage of the Simplified Hull Girder Subjected to Underwater Explosion Bubble
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 13
Issue 4
10.3390/app13042319
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

A Joint Channel Estimation and Compression Method Based on GAN in 6G Communication Systems

Appl. Sci. 2023, 13(4), 2319; https://doi.org/10.3390/app13042319
by Ying Du 1,2, Yang Li 2, Mingfeng Xu 2,*, Jiamo Jiang 2 and Weidong Wang 1
Reviewer 1: Anonymous
Reviewer 2:
Sisay Tadesse Arzo
Appl. Sci. 2023, 13(4), 2319; https://doi.org/10.3390/app13042319
Submission received: 20 October 2022 / Revised: 25 January 2023 / Accepted: 7 February 2023 / Published: 10 February 2023
(This article belongs to the Special Issue Beyond 5G and 6G Communication Systems)

Round 1

Reviewer 1 Report

Please consider the following comments and questions for revision as:

(1) Specify in an understandable way, G(z; theta_g) and D(x; theta_d) for proving the correctness of the simulation results and for being readily reproduced by interested readers.

(2) This reviewer thinks that the number of iterations and the learning rate should be heavily dependent. Please explain how this issue should have been considered.

(3) Please explain specifically the reason why the NMSE is not reduced drastically as the SNR increases. Please explain the dependency of SNR and NMSE(in log-scale). If necessary, give the reason to be saturated as the SNR increases.

(4) Please explain specifically the dependency of the NMSE on the number of pilots, and also the dependency of the NMSE on both the number of pilots and the mobile speed. If possible, please give a qualitative explanation.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

1. The author presented an interesting channel estimation technique using generated adversarial networks (GAN). With the evaluation of the proposed approach, they have shown the improvement of the proposed method in that they have achieved a performance gain of more than 2 dB with a pilot reduction of 75% when SNR is 10 dB. 

2. The only concern is why the authors would like to use 6G in the title which has not even been clearly defined. The method can be applied with 5G and beyond 5G too. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

- The authors are asked to highlight the improvements of their manuscript over [22]

- Please define "compression rate" term that you use

- does the noise variance really depend on (i,j) ?

- in the simulations, the maximal propagation delay of 300ns is relatively small with respect to OFDM symbol duration. Can you discuss this?  Is there any cyclic prefix used?

- can you provide more details on the Wiener method used as a reference and on its implementation?

- the Rxx in eq. 4 should not be called the correlation coefficients

- English must be checked carefully, there are really TOO MANY typos, errors... !

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop