Experimental Method to Estimate the Density of Passengers on Urban Railway Platforms

Round 1

Reviewer 1 Report

This study estimates the density of passengers waiting to board on urban railway platforms. The logic of this manuscript is clear and the result is reasonable. The following comments may help to improve this manuscript.

1.     The result of the experiment in this study should be introduced and summarized in the abstract.

2.     The authors said that the new method is proposed to estimate the density of passengers waiting to board. However, the difference between the proposed method and other methods is not compared. If possible, the result of using the proposed method and other methods should be compared to show the effectiveness of the proposed method.

3.     Some detailed suggestions for controlling passengers on the platform should be introduced according to the result, which can enhance the practicality of this manuscript.

4.     The experiment is carried out in this study. However, I am concerned that the experiment cannot reflect passengers’ real actions on the platform. How can you make the experiment close to the real situation?

Finally, there are some grammar mistakes, such as "These interactions are caused because off the high level of demand at the PTI ". 

Author Response

Thank you very much for your comments. We tried to address all of them as best as possible (see attached file).

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper focused on the Experimental method to estimate the density of passengerswaiting to board the train on urban railway platforms The subject matter of this manuscript fits the journal's scope, and the information included in the manuscript seems not to have been published in any other publication so far. However, it seems difficult to adequately evaluate the value of this study because the explanation of the significance of the study, the description of the interpretation and usefulness of the results obtained by the analysis, and the explanation of the model are insufficient. I would like to ask the authors to consider responding to the following comments:

(1)    Authors need to re-write the abstract, because some statement are not linked each other. Such as To solve this problem, a new method is developed to estimate the density of passengers
waiting to board on urban railway platforms by means of laboratory experiments, which is the main objective of this study. For the development of the method, the use of computer vision is necessary, through training of neural networks and image processing.

(2)    Would you explicitly specify the novelty of your work? What progress against the most recent state-of-the-art similar studies was made?

(3)    The Introduction section should be improved. It should be dedicated to presenting a critical analysis of state-of-the-art related work to justify the study's objective. In addition, critical comments should be made on the results of the cited works.

(4)     The main objective of the work must be written in a more precise and concise way at the end of the introduction section. Please carefully check recent literature and discuss/cite as you see fit, and update your reference list. Modeling of machine learning with SHAP approach for electric vehicle charging station choice behavior prediction. Public Preferences Towards Car Sharing Service: The Case of Djibouti

(5)    A summative table highlighting the outcomes from previous research is expected at the end of the introduction section

(6)    There is a room to improve the research methodology for publishing in an international journal. Furthermore, the numerical experiments were insufficient.

(7)    The reviewer thinks some figures related to the computation results should be presented to improve the quality of this paper.

(8)    The conclusion section provides a lack of contributions to this manuscript. Provide the key features, merits, and limitations of the proposed approach to clarify the precise boundary of the algorithms. The implication of the proposed method is also required.

(9)    This paper is generally well-written, but I found multiple typographic and editorial errors throughout the entire manuscript, including the equations. The authors need to proofread again carefully.

Author Response

Thank you very much for your comments. We tried to address all of them as best as possible (see attached file).

Author Response File: Author Response.pdf

Reviewer 3 Report

1. In addition to the solution in this paper, I think there are two other possible approaches. The first one is to train a machine learning model based on swipe card data to infer the number of people on the platform. The second one is to use cell phone signaling data to estimate the number of people on the platform. The authors can discuss these solutions and can cite the following references 'DeepPF: A deep learning based architecture for metro passenger flow prediction', 'A tailored machine learning approach for urban transport network flow estimation. Transportation Research Part C: Emerging Technologies'

2. This paper lacks a methods section. This paper is based on target detection techniques in computer vision, but does not present anything related to deep learning (equations, graphs, network structures, improvements, etc.)

Author Response

Thank you very much for your comments. We tried to address all of them as best as possible (see attached file).

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have addressed my concern. I recommend to publicate this manuscript. Before publication, I suggest authors proofread this manuscript carefully.

Author Response

Comment: The authors have addressed my concern. I recommend to publicate this manuscript. Before publication, I suggest authors proofread this manuscript carefully.

Answer to Comment: Thank you very much for reviewing our article. We really appreciate all the kindly suggestions you have made.

Reviewer 2 Report

The authors addressed all the comments adequately

Author Response

Comment: The authors addressed all the comments adequately

Answer to Comment: Thank you very much for reviewing our article. We really appreciate all the kindly suggestions you have made.