Next Article in Journal
Gear Integrated Error Determination Using the Gaussian Template Convolution-Facet Method
Previous Article in Journal
Examining Modulations of Internal Tides within An Anticyclonic Eddy Using a Wavelet-Coherence Network Approach
 
 
Article
Peer-Review Record

An Experimental Demonstration of 2D-Multiple-Input-Multiple-Output-Based Deep Learning for Optical Camera Communication

Appl. Sci. 2024, 14(3), 1003; https://doi.org/10.3390/app14031003
by Duy Tuan Anh Le, Huy Nguyen and Yeong Min Jang *
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Appl. Sci. 2024, 14(3), 1003; https://doi.org/10.3390/app14031003
Submission received: 19 December 2023 / Revised: 22 January 2024 / Accepted: 22 January 2024 / Published: 24 January 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The featured paper presents an interesting topic. However, the paper is full of errors and lacks a presentation of the results obtained. The paper needs proofreading, phrases like ""human participants plants"  appear. The authors assume fog as a light source. The authors assure that the light seen has no effect on human health. However, there is epilepsy whose attacks can be caused by flashing light. In the introduction, the authors do not explain why rotation is extremely important for OOC communication. The authors should present the difference in the rolling shutter and the global shutter. Figure 1 shows the transmitter and receiver. The communication is unidirectional. There is no justification for calling these two separate devices a transcivier (a combination of transmitter and receiver in one device). Likewise, during the experiment, the transmitting and receiving device are separate devices. The caption of figure 1 does not agree with the content of the drawing. No description of the neural network architecture used, other than to say that the YOLO algorithm was chosen. No justification for this choice. No description of the algorithm. No raw input signal presented. The caption of figure 3 does not show the results. In the description of Eb N0 once it appears in subscript once it does not. The formula 3 is not complete. No explanation of all its components. Formula 4 is incorrect, no explanation of "efrc". No explanation of the abbreviation AWGN. The formula is not explained. What is r(t) and where is it used. Figure 10 does not represent what it is supposed to represent. It does not depict a change in exposure time. No schematics of the equipment in the laboratory used for the experiment. No description of the software. And most importantly. No results that are described in the conclusion. The authors, apart from one table from which not much is clear other than throughput and one graph where they do not show what they describe, have not shown any results. In particular, the effect of speed, rotation, and jamming on the proposal presented. The description of the algortym is also very sketchy and does not allow for an experiment. The algorithm for converting data into characters on the LED array is not shown, the algorithm for determining the serial number of the data packet is not shown, the method for selecting the length of the serial number of the data packet is not shown. The presented article, except for the introduction with a literature review, has no scientific value at the moment.

 

Comments on the Quality of English Language

Typos, unintelligible phrases.

Author Response

Please check attached file

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Comments on: An Experimental Demonstration of 2D-MIMO-based Deep Learning for Optical Camera Communications

 

An interesting experiment indeed.

 

The major concerns are two:

 

1. The equations are presented in chaos. Here are some examples:

(3): what does (t) mean, should it be I(t)? ;

(5) why reads 2. I(t), instead of 2I(t)?

(7) and (8), why they are written in different fonts? What is the default font for formulars in this paper?

And more ……

2. Details were missing

The paper used a paragraph to describe channel coding, i.e., FEC, but what is the channel coding here? CC, LDPC, Polar?

 

It appears that the channel is AWGN (see (5)), but it is not possible that the wireless channel here is AWGN. The channel is more like Rice.

 

The transmit power is not known, which prevents correct interpretation of the results.

And more ……

Author Response

please check attached file

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The Authors corrected their article. I think it is suitable for publication in the form submitted.

Author Response

Thank you for your help.

Reviewer 2 Report

Comments and Suggestions for Authors

The authors upload a video to demonstrate the outcome, which seems interesting. Though the revised version failed to address the concerns we raised, the scheme and results perhaps interest some readers. So I give a pass.

Author Response

Please check the attached file.

Author Response File: Author Response.pdf

Back to TopTop