A Deep Learning-Enhanced MIMO C-OOK Scheme for Optical Camera Communication in Internet of Things Networks

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this paper, the authors introduce a deep learning-enhanced MIMO C-OOK scheme, where deep learning is used for both light sources detection/tracking and signal decoding. Proof-of-concept experiments show the feasibility of proposed scheme. Nevertheless, there are some critical issues need to be addressed before a final recommendation can be made.

1. For deep learning-based light sources detection/tracking, YOLOv11 is used which is actually quite well-known and mature. So what is the novelty of your scheme and what are the key contributions?

2. For deep learning-based signal decoding, it seems two neural networks are used to predict the preamble and the threshold, respectively. However, the detailed principles shown in Fig. 4 are not described clearly. 

3. As above, three individual AI tools are used to facilitate light sources detection/tracking, preamble prediciton, and threshold prediciton independently, making the overall system much more complex. Is it possible to finish two or three tasks using one network? 

4. In Fig. 10, the Y axis is not shown properly and the velocity values in the caption and title are different.

Author Response

Please check the attached file.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Please refer to the attachment.

Comments for author File: Comments.pdf

Author Response

Please check the attached file.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper investigates a deep learning–enhanced MIMO C-OOK scheme for Optical Camera Communication (OCC), targeting long-range and mobility-aware Internet of Things (IoT) scenarios. The topic is relevant to the Photonics and Optical Wireless Communication (OWC) community, particularly in the context of IEEE 802.15.7/7a standards and camera-based receivers. The integration of deep learning for both LED detection/tracking and data decoding under mobility is a promising direction. However, while the proposed approach is technically sound, the manuscript requires substantial improvements in clarity, rigor, and presentation before it can be considered for publication. Followings are the specific comments from the reviewer.

1). Claims regarding health risks of RF systems are strong and should be moderated or better justified.

2). The research gap and novelty relative to existing DL-based OCC and MIMO C-OOK works are not clearly articulated.

3). A clearer comparison with recent related studies is needed.

4). The authors introduce VLC, MIMO shortly and directly comes to OCC. It would be better to provide some references to MIMO VLC and their challenges. Followings are some of the suggested papers to refer.

a). Sejan, M.A.S.; Rahman, M.H.; Aziz, M.A.; Kim, D.-S.; You, Y.-H.; Song, H.-K. A Comprehensive Survey on MIMO Visible Light Communication: Current Research, Machine Learning and Future Trends. Sensors 2023, 23, 739.

b). K. W. S. Palitharathna, C. Skouroumounis and I. Krikidis, "Liquid Lens-Based Imaging Receiver for MIMO VLC Systems," in IEEE Transactions on Communications, vol. 73, no. 11, pp. 11663-11678, Nov. 2025. 

5). The overall system architecture is reasonable, but key technical details are missing.

6). YOLOv11-based LED detection is promising, but, training details (dataset split, hyperparameters, validation) are insufficient. The choice of YOLOv11 over simpler models is not justified.

7). The link between RMSE and BER performance is not clearly explained.

8). Several figures have readability issues (small fonts, low clarity).

9). Figure captions lack sufficient explanatory detail.

10). Notation is occasionally inconsistent across figures and text.

Comments on the Quality of English Language

The use of professional English is poor and need further improvement.

Author Response

Please check the attached file.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The revised paper can be accepted for publication.

Reviewer 2 Report

Comments and Suggestions for Authors

The author has addressed all of my queries, and I recommend publication in the current form.

Reviewer 3 Report

Comments and Suggestions for Authors

Authors have well addressed all the comments from the reviewer. No further comments. Thank you.