Research on Indoor Visible Light Location Based on Fusion Clustering Algorithm

Round 1

Reviewer 1 Report

Revise the title by ignoring Research keyword. Include the term Fusion in the first sentence of the Abstract section. Supply a few sentences in the Introduction section on the significance of real-time positioning and indoor positioning accuracy in the context of optical wireless communications (e.g., VLC).  What channel model is considered in this study and How the RSS (or SINR) is affected under NLOS communication by path loss? What is the computational complexity of the proposed algorithm? It’s better to illustrate K-medoids algorithm either in flow chart or pseudo format.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments to the Author

 

This paper proposes a new location fingerprint location method based on a clustering-based approach that embodies the idea of rough location first then fine location. It is an interesting research topic with many potential application areas. However, there are several points that need to be addressed to improve the quality of the manuscript.

 

Suggestions to improve the quality of the paper are provided below:

 

1.     The authors should include a few examples in the Introduction section of the real-world applications of indoor localization systems. Indoor positioning is leveraged intensely especially in the building domain where several popular real-world applications are worth mentioning to target a large audience. These building applications include emergency management, smart energy management and HVAC controls and occupancy detection. Please review the following established works as a good starting point to highlight the important applications where indoor positioning leveraged.

 

Indoor localisation for building emergency management

10.1109/IUCC-CSS.2016.013

 

Indoor localisation for smart energy management

https://doi.org/10.1016/j.buildenv.2022.109472

 

Indoor localisation for smart HVAC controls

https://doi.org/10.1145/2517351.2517370

 

Indoor localisation for occupancy prediction

https://doi.org/10.1016/j.buildenv.2022.109689

 

2.     Before diving straight into indoor visible light positioning, it is important to give a brief overview of different indoor localisation approaches. Wifi-based and Bluetooth Low Energy-based localisation technologies are amongst the most popular wireless technologies used for indoor localisation. Please refer to the following paper [1] as a good starting point and provide a short discussion about both approaches before explaining why indoor visible light position was chosen for this study.

 

[1] https://doi.org/10.1016/j.buildenv.2020.106681

 

3.     Given that the initial cluster centres for the K-medoids algorithm are randomly selected, this usually results in slightly different clusters at the end when the clustering algorithm is rerun-ed. Please discuss/clarify how this issue is resolved. Also, discuss how the value “k” is determined in this case.

 

4.     Similarly, it was mentioned that the initial selection of Eps and Minpts have a great influence on the results of the clustering effect using DBSCAN. Please clarify how these values were chosen.

 

5.     Please include a discussion section on the limitations of the existing approach and elaborate on how they can be improved in future works. For instance,

·       The proposed improved fingerprinting method requires the study area to be divided into multiple clusters and performing separate analysis for each cluster to identify the optimal clustering algorithm and k value. How scalable will this approach be for larger spaces and more complex room layouts? How will this be resolved in the future?

 

6.     Minor comments

·       The following sentence was found in Page 6 “the text following an equation need not be a new paragraph. Please punctuate equations as regular text.” which appears to be some template text. Please review the manuscript thoroughly and remove all irrelevant content.

·       It is hard to compare Figure 7 and 10 since they are found in very different parts of the manuscript. Please consider placing them closer together/next to each other.

·       Please include the units for measuring positioning error in Table 3.

Comments for author File: Comments.pdf

There were some minor issues with the quality of English, which were highlighted in the comments. Please make sure to address them accordingly.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Please kindly find the attached report.

Comments for author File: Comments.pdf

Moderate editing of English language usage is needed. The quality of English language in this manuscript appears to be generally good. The language is appropriately technical and scientific which is important for effectively conveying the research content. However, there a few areas where improvements could be made to enhance overall clarity and fluency of the manuscript. These include:

- Sentences structure: some sentences are quite long and could be simplified or divided to improve the readability.

- Punctuations.

- Clarity and specificity.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Authors have thoroughly address the comments.

Reviewer 2 Report

Thank you for taking the time to address my comments. I believe the quality of the manuscript has been significantly improved, and it is now ready for publication.

There are no major issues with the manuscript's quality of English.