Next Article in Journal
Research on Anti-Occlusion Correlation Filtering Tracking Algorithm Based on Adaptive Scale
Next Article in Special Issue
Travel-Time Estimation by Cubic Hermite Curve
Previous Article in Journal
ICT Use, Digital Skills and Students’ Academic Performance: Exploring the Digital Divide
 
 
Article
Peer-Review Record

Methodological Study on the Influence of Truck Driving State on the Accuracy of Weigh-in-Motion System

Information 2022, 13(3), 130; https://doi.org/10.3390/info13030130
by Shuanfeng Zhao *, Jianwei Yang, Zenghui Tang, Qing Li and Zhizhong Xing
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Information 2022, 13(3), 130; https://doi.org/10.3390/info13030130
Submission received: 6 January 2022 / Revised: 22 February 2022 / Accepted: 23 February 2022 / Published: 3 March 2022
(This article belongs to the Special Issue Soft Computing in Intelligent Transportation System)

Round 1

Reviewer 1 Report

This paper proposes to add Spatial Pyramid Pooling (SPP) network and Cross Stage Partial (CSP) network to the original network model based on YOLOv3 network model to improve the learning ability of the convolutional neural network while making the original network more lightweight.

In general, this paper organizes well. The framework of this paper is clear. The contribution of this paper is clearly stated. I have some comments to further polish this paper.

  1. The authors should briefly explain the origin network model before introducing their work in the abstract
  2. The value of this paper should be further emphasized.
  3. The title of section 3 is “related works”, so where is your work?
  4. Reorganize the manuscript, add a section “problem statement” to elaborate the problem you aim to address and add a section “model formulation” to elaborate the method you designed to address this problem.
  5. More case studies should be conducted to validate the proposed method.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper proposed a method to track the position, wheelbase and motion state of the actual vehicle from the surveillance video by machine vision techniques and then investigated whether this affects the accuracy of the weighing system and the magnitude of the effect on the accuracy under different driving states. This study is of great significance to improve the accuracy of highway WIM. This paper needs to be further supplemented and improved. As the following:

1. There are a lot of abbreviations in this article. The abbreviation in the text should be written in full for the first time, such as Page 2 line 70 “LMS” , Page 3 Line 134 “CBAM” and so on.
2. In the section 4.1 Data collection. In order to facilitate the evaluation of the algorithm. the total number of samples and sample distribution need to be clear.
3. The data analysis in Figure 16 is not clear enough. Figure 16 (a) and (b) are the signals generated by the same vehicle passing through the load cell in two different motion state?  It can be seen from the signal amplitude that the signal in figure 16 (a) is significantly larger than that in figure 16 (b)? Whether it can be considered that it is not the same car.

4.  Whether the curves of the four colors in Figure 16 represent the four weighing sensor cell . The same weighing cell is rolled by the front and rear wheels once, and the two peaks of the same color curve represent the front and rear wheels. Therefore, 1-left and 2-left should be on the same color curve. 1-right and 2-right should be on the same color curve. Is the wheel marked on the original signal in Figure 16 wrong? It is suggested to draw the relative position between the tire and the weighing cell at different stages during the driving process of the vehicle and correspond to the peaks of the curves one by one.
5. It can be seen from Figure 16 (b) that when 1-left passes through the first row of sensors, the left and right wheels on the same axis are very different. This should be caused by the left and right eccentric load of the car. The large difference between the front and rear peaks of the same color curve should be caused by the large difference between the front and rear axle loads.  The data results in Figure 16 and table 3 suggest re analysis. Whether the resulting error is caused by acceleration and deceleration needs further analysis.

6. In Conclusions, line 383-385 “some of them cannot be weighed accurately due to the variable driving state of the vehicle during weighing, which leads to the shift of the vehicle's center of gravity back and forth”.  Further explain how acceleration and deceleration affect the change of vehicle center of gravity. Whether this conclusion only be suitable for vehicles carrying liquid.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The paper is relatively well-written and has some quality data and results reported.  There are a few suggestions that the authors may wish to consider and respond to further improve the article.  

1) The focus of the paper is not very definite.  The title sets out the objective of studying "the influence of truck driving state on the accuracy of the weigh-in-motion system", however in the abstract, it seems that proposing the method to do so is the purpose, and in the main text and in the conclusions, it's somewhere in between.  After reading through, it's leaning more to the methodological side than the influences, as there are not sufficient data and results presented for the latter.  The authors may need to make up their minds and give them a more definite presence in the paper.  A practical suggestion is to alter the title a bit to e.g., "Methodological Study on the influence..." to better reflect the contents of the paper.

2) In the abstract, line 12, "the driving status of the truck will affect...", where "may" should be used instead of "will", as it's either not proven yet or it's not established yet, and secondly, "states" should be used instead of "status", as the former should be what the authors are aiming to study.  In line 14, it's not clear what "original" refers to?  In line 17, "effect" should be "effective".  

3) Figure titles and Table titles should be centered in the entire paper.

4) Line 173, Figure 3 title contains unknown words "This is a figure".  

5) Line 215, instead of "equation 2", it should be "Equation (2)."

6) Line 217, mathematical vector symbols instead of the whole vector (or matrix) are shown.  This would also eliminate the huge line gaps created as a result of the current arrangements.  

7) Line 249, a more proper name than "homemade dataset" should be used, e.g. considering using "training dataset".

8) Lines 273 to 277, Fig. 9(a) and Fig. 9(b) instead of Fig. (a) and Fig. (b), as well as "8m by 12m" and "8m by 2m" instead of "8m 12m" and "8m2m" respectively.

9) Line 297, and in the associated figures, the Purple segments of curves are actually hard to be distinguished from the Magenta portion of curve segments connected to them.  It's 3D and the colors are too close.  

10) Lines 301 to 311, is the authors referring to "a truck" or "a vehicle"?  What do the authors mean when "this truck" is used?  The authors should refine their statements and make them clearer.  

11) Although it's eye-catching to view the results in 3D, it should be better if the x- and y- scale can be such that the vehicle position in any given instance can be more clearly shown, otherwise, the current representation is no better than a straight line.  In fact, most WIM sections are straight, therefore what is meaningful is to show in greater detail the trucks' positions on the WIM scale, and to see whether such distribution of truck positions on the scale affects the accuracies.  If the authors have the information, what would be more interesting would be to show the vertical profile of the trajectory as the up and down motion of the trucks may affect the accuracy as well.  In any case, the authors should include a legend in Figures 11 to 13.

12) In the conclusion, line 374, instead of "Different drivers have different driving behaviors, ..." it may be better to present it in this way "Driving behaviors vary across drivers, ...".  The term "dynamic weighing system" suddenly appear in this section, which for the sake of consistency, the term "WIM system" or "Weigh-in-motion system" should be used instead, as it's more commonly used and more commonly referred to in the main text, in fact, to a greater extent, such similar terms should be unified and made consistent throughout the paper.  In line 383, it seems that "6-axle truck" and associated discussion has not been or at least has not been explicitly mentioned in any parts of the paper.  If those are the points that the authors wish to raise in the conclusions, more information should be added or made more explicitly in the discussion in the main text.

Author Response

请参阅附件。

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors has revised the manuscript and responded the comments. This paper canbe published.

Back to TopTop