You are currently viewing a new version of our website. To view the old version click .
by
  • Xianhao Lin1,2,3,
  • Fangchen Hu1,2,3 and
  • Nan Chi1,2,3,*

Reviewer 1: Anonymous Reviewer 2: Anonymous Reviewer 3: Anonymous

Round 1

Reviewer 1 Report


Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

In order to solve the too high complexity requirement of traditional DNN-based waveform-to-symbol converter in underwater visible light communication (UVLC), this manuscript proposes a cascaded receiver consisting of a DNN-based waveform-to-symbol converter and modified NN-based DD-LMS.This manuscript finds it high efficient to achieve a balance between computation complexity and communication performance by using front-stage DNN-based waveform-to-symbol converter to mitigate the majority of ISI and signal nonlinear distortions and then using modified NN-based DD-LMS to eliminate remaining ISI and distortions.The experimental data in this paper show that the proposed method greatly reduces the computational complexity compared with the traditional DNN-based waveform-to-symbol converter. It is a nice paper, this reviewer has no further comments.

Author Response

Thank you so much for reading our paper carefully and giving the above encouraging comments.

Author Response File: Author Response.docx

Reviewer 3 Report

The authors propose a cascade receiver consisting of a DNN-based waveform-to-symbol converter and a modified NN-based DD-LMS, to improve the issues related to bandwidth limitation, and communication distortions that show up in underwater VLC based on LEDs. The used cascade receiver is experimentally verified in a 1.2m optical path underwater, showing improved performance.

The topic is relevant, and the paper is generally well organized even if a bit heavy to read, but suitable for publication.

My observations:

- There is no consideration about maximum distance reachable. In fact, for underwater communications it is not so much important the bit rate but the distance that can be reached.

- Double check acronyms.

- Recommended to provide features about the blue LED used in experiment as optical power, divergence of the spotlight, etc.

- Only journal in English language should be considered in bibliography.

Author Response

Please see the attachment.

Author Response File: Author Response.docx