A Cluster-Then-Route Framework for Bike Rebalancing in Free-Floating Bike-Sharing Systems

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors Overall the paper is interesting well structured and easy to understand ( apart from the mathematical notation)   Few suggestions and clarification are noted next.   Line 122...improved Max-Min Ant System ... to mention it above through the introduction.    Section 2. Sugest to structure the Literature works. i.e provide a summary table including e.g. year ; category statics/dynamics; methods;models; dataset; main findings....     And to precisely define/mention  the State-of-the-art.    Section 3.  any of the previous approaches' dataset are reusable?   Can you also share your data for public. ?   Is the time window for your data 1-9 may 2019.... are you reusing this data or how you obtained it,  Now?     Fig 2.b. the red dots are bikes , or a cluster of bikes    bicycles vs bikes.. make it consistent through the manuscript   Line 420 to 424 revise the definition of notation "  O^ps " .. 'omega' represents all    To make/amend a transition sentences btw subsections e.g 5.1 and 5.2 , 6.1 and 6.2 and so on...    449...and its allele value.... to add a short description    the length of the vehicle route (Eq. 16),...are you considering  the traffic contingency cost here  or the  distance length only.   Fig 9 as well other fig's; define the colours which refers to the bikes.    Fig 10. If we considered 5am in the next day are we expecting similar distribution of bikes.. is this valid for working days vs weekends   Fig 10. Revise the caption to include the time variation.   Line 834...obtain the following function expression:...is missing    872 .."while the total distance travelled by the service vehicles is 215.4 kilometres"...Vs. what; compared to what if u use single sub-period; i.e. the % of reduction in distance Comments on the Quality of English Language

Overall is fine easy to read and understand 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

-The authors studied the dynamic bike-sharing rebalancing problem (DBRP) in free-floating bike-sharing systems (FFBSSs) that allow for bikes to be rented and returned almost anywhere in the service area. They introduced a Density- and Grid-Based Clustering Algorithm with Multi-level Density Thresholds to locate rebalancing nodes.

-The following major corrections are required:

Section 1: Introduction

-The introduction section is too general, and it introduces concepts that are well known about the dynamic rebalancing in free-floating bike-sharing systems. The introduction does not stimulate to go ahead with the remaining of the paper because it does not introduce any really new topic/solution. Furthermore, "the research motivation at the introduction section is missing. Please rewrite this section.

 Section 2: Literature review

-In this section, the authors should be describe some of the research works about the dynamic rebalancing in free-floating bike-sharing systems, while some of the papers that should have be included are:

https://ieeexplore.ieee.org/abstract/document/10164286

https://www.sciencedirect.com/science/article/pii/S2046043021000691

https://onlinelibrary.wiley.com/doi/abs/10.1002/ett.4127

https://www.sciencedirect.com/science/article/abs/pii/S0378437122009670

https://link.springer.com/article/10.1007/s10586-019-03026-9

https://ieeexplore.ieee.org/abstract/document/10133876

…..

-In addition, a conclusion of related work in the forms of a table in terms of evaluation tools, utilized techniques, performance metrics, datasets, advantages, and disadvantages could reconcile from other researchers work to the own one.

Sections 3-6: Proposed Solution

-Please provide a sequence diagram to show the interaction between components of the proposed framework according to Figure 1.

-Your proposed solution is very similar to the following papers. What is the difference between proposed model and mentioned papers?

https://ieeexplore.ieee.org/abstract/document/10164286

https://www.sciencedirect.com/science/article/pii/S2046043021000691

 

-What is the overhead (time complexity) proposed solution? Please provide a subsection to discuss about the overhead (time complexity) of proposed Algorithms 1-2.

Section 7: Results and discussion of the numerical study

-The evaluation is incomplete. I would like to see an evaluation on the proposed solution in terms of execution time different scenarios.

-The evaluation lacks the minimum rigor required for the scientific comparison of stochastic algorithms. Specifically, statistical tests of the hypothesis should be used to determine whether the differences shown in the figures are statistically significant or due to chance.

-Paper needs some revision in English. The overall paper should be carefully revised with focus on the language: especially grammar and punctuation.

-Overall, there are still some major parts that the authors did not explain clearly. Some additional evaluations are expected to be in the manuscript as well. As a result, I am going to suggest Major revision the paper in its present form.

Comments on the Quality of English Language

-The authors studied the dynamic bike-sharing rebalancing problem (DBRP) in free-floating bike-sharing systems (FFBSSs) that allow for bikes to be rented and returned almost anywhere in the service area. They introduced a Density- and Grid-Based Clustering Algorithm with Multi-level Density Thresholds to locate rebalancing nodes.

-The following major corrections are required:

Section 1: Introduction

-The introduction section is too general, and it introduces concepts that are well known about the dynamic rebalancing in free-floating bike-sharing systems. The introduction does not stimulate to go ahead with the remaining of the paper because it does not introduce any really new topic/solution. Furthermore, "the research motivation at the introduction section is missing. Please rewrite this section.

 Section 2: Literature review

-In this section, the authors should be describe some of the research works about the dynamic rebalancing in free-floating bike-sharing systems, while some of the papers that should have be included are:

https://ieeexplore.ieee.org/abstract/document/10164286

https://www.sciencedirect.com/science/article/pii/S2046043021000691

https://onlinelibrary.wiley.com/doi/abs/10.1002/ett.4127

https://www.sciencedirect.com/science/article/abs/pii/S0378437122009670

https://link.springer.com/article/10.1007/s10586-019-03026-9

https://ieeexplore.ieee.org/abstract/document/10133876

…..

-In addition, a conclusion of related work in the forms of a table in terms of evaluation tools, utilized techniques, performance metrics, datasets, advantages, and disadvantages could reconcile from other researchers work to the own one.

Sections 3-6: Proposed Solution

-Please provide a sequence diagram to show the interaction between components of the proposed framework according to Figure 1.

-Your proposed solution is very similar to the following papers. What is the difference between proposed model and mentioned papers?

https://ieeexplore.ieee.org/abstract/document/10164286

https://www.sciencedirect.com/science/article/pii/S2046043021000691

 

-What is the overhead (time complexity) proposed solution? Please provide a subsection to discuss about the overhead (time complexity) of proposed Algorithms 1-2.

Section 7: Results and discussion of the numerical study

-The evaluation is incomplete. I would like to see an evaluation on the proposed solution in terms of execution time different scenarios.

-The evaluation lacks the minimum rigor required for the scientific comparison of stochastic algorithms. Specifically, statistical tests of the hypothesis should be used to determine whether the differences shown in the figures are statistically significant or due to chance.

-Paper needs some revision in English. The overall paper should be carefully revised with focus on the language: especially grammar and punctuation.

-Overall, there are still some major parts that the authors did not explain clearly. Some additional evaluations are expected to be in the manuscript as well. As a result, I am going to suggest Major revision the paper in its present form.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

I think there are some major revisions needed in this submission. Please address all comments:

1) One of the biggest issues with this submission is the missing element of demand prediction. Without prediction, you cannot have a practical model. Demand prediction should be incorporated.

2) This paper clusters first and routes second. This should be acknowledged. Maybe title can be "A cluster-then-route framework..."

3) In the second line of introduction, authors claim bike sharing complements other modes. However, later studies show that actually substitute other modes. I encourage you read and cite following paper and discuss that substitution makes bike sharing more important:

Basak, E. and Iris, Ç., 2023. Do the First-and Last-Mile Matter? Examining the Complementary and Substitution Effects of Bike-Sharing Platforms on Public Transit. SSRN Pre-print.

4) I do not think you actually do dynamic rebalancing as you do not consider demand prediction. You still have known demand and planning relies on known demand. Therefore, I recommend removing dynamic from the title and replace it with bike rebalancing. Therefore title can be "A cluster-then-route framework for bike rebalancing in free-floating bike-sharing systems"

Comments on the Quality of English Language

-

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Thanks to authors for the detailed response and additions I read through the comments and skimmed the revised PDF, The updates did improve the paper a lot. I would be happy to recommend this paper for publication

 

Comments on the Quality of English Language

Thanks to authors for the detailed response and additions I read through the comments and skimmed the revised PDF, The updates did improve the paper a lot. I would be happy to recommend this paper for publication

 

Author Response

Great thank you for your positive feedback and recommendation. Your insights and suggestions have been invaluable in enhancing the quality of our paper. We look forward to the final paper for publication.

Reviewer 3 Report

Comments and Suggestions for Authors

A revision is needed:

1. Line 4, it should be Basak and Iris [4] found that...

2. Line 113-116 is not well written. You can rewrite.

3. section 5.1, did you barrow these equations from literature? You should cite the right source for those equations (9-11) and procedures.

4. I think you can remove section 8.6. It does not tell us much.

5. I think you can publish randomly generated data in a github platform and give github link in the paper. Therefore, other researchers can use that as well.

6. On line 550, you can note that neareast neighbor based methods are used in other micromobility modes such as [57] and cite [57]: https://doi.org/10.1016/j.trd.2022.103371

Comments on the Quality of English Language

-

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 3

Reviewer 3 Report

Comments and Suggestions for Authors

Accept as is.