An Algorithm to Generate a Weighted Network Voronoi Diagram Based on Improved PCNN

Round 1

Reviewer 1 Report

The article is about the application (and adaptation) of the popular parallel mechanism of the PCNN neural network. A method is sufficiently described, and adaptation for Voronoi segmentation is not complicated but relatively novel. My comments are the following:

• Comparisons with SANET tool are not easy to understand for the reader - maybe both figures should be parallel on the page with explicit visual hints.
• Allocation is the traditional issue in geoinformatics with many implementations in network analysis - maybe some more reflection of the allocation algorithms with their obstacles sold be useful. 
• The main reason for the parallelization of the allocation problem is the speed of processing - there is no time-related comparison with SANET or another method.

Author Response

Dear Editors and Reviewer:

First, we would like to thank the reviewer and the editor for the positive and constructive comments and suggestion for our manuscript entitled “An Algorithm to Generate Weighted Network Voronoi Diagram based on Improved PCNN” (ID: applsci-1718627). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portions are done using the “Track Changes” function. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

1. Comment 1: Comparisons with SANET tool are not easy to understand for the reader - maybe both figures should be parallel on the page with explicit visual hints.

Response 1: Thanks for your suggestion, and we have parallel placed the comparison figures, as shown in page 13, Figure 11.

2. Comment 2: Allocation is the traditional issue in geoinformatics with many implementations in network analysis - maybe some more reflection of the allocation algorithms with their obstacles sold be useful.

Response 2: Thanks. As you kindly reminded, there are many allocation algorithms, and among these algorithms, Voronoi diagram and weighted Voronoi diagram are the most classical algorithms. Comparing with the Voronoi diagram, weighted Voronoi diagram take account of the points’ weight, so the comparative experiment based on the weighted Voronoi diagram has been done, as shown in page 11, Figure 10.

3. Comment 3: The main reason for the parallelization of the allocation problem is the speed of processing - there is no time-related comparison with SANET or another method.

Response 3: Thanks for your suggestion, we have added a table and corresponding descriptive text about the comparative performance parameter of the algorithm, as shown in Table 1 (page13) and text revised in “Track Changes" in page12.

 We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

Author Response File: Author Response.docx

Reviewer 2 Report

The paper shows an alternative way of constructing weighted voronoi diagrams - it is submitted as a review article. This is the reason I have put its originality as average. The paper is well presented and  discussed and easy to follow. I do think the paper is well written and edits in English are well written. So some final polishing is necessary but it is again a minor change to the article

Author Response

Dear Editors and Reviewer:

First, we would like to thank the reviewers and the editor for the positive and constructive comments and suggestion for our manuscript entitled “An Algorithm to Generate Weighted Network Voronoi Diagram based on Improved PCNN” (ID: applsci-1718627). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portions are done using the “Track Changes” function. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

1. Comment 1: I do think the paper is well written and edits in English are well written. So some final polishing is necessary but it is again a minor change to the article.  

Response 1: Thanks for your comment，we have checked our manuscript carefully and made some changes, as follows:

• We have checked our language expression, article format and logical structure again carefully, which are modified using“Track Changes" function, as shown in page 1,2, 4, 6, 7, 8, 9, 12,13.
• We have added comparisons and data analysis of the experiments, as suggested by another reviewer, shown in page 11, 12, 13.

 We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

Author Response File: Author Response.docx