Novel Neural-Network-Based Fuel Consumption Prediction Models Considering Vehicular Jerk

Round 1

Reviewer 1 Report

Line 1: Only the word “Article” must appear here. 

Line 11: The space mut be removed after “this issue,  “

Line 24: add acronyms for “World Meteorological Organization”

Line 126: The Figure caption must be same page as the Figure

Section 2; there is no in-text citation of the Figure 1 (a) or (b), just Figure 1

Line 148: The caption for Table 1 must be same page with Table

Section 3, there is no in-text citation of Figure 3 (a), etc 

Line 186: The Eqn is not numbered, it must also be cited in-text

Sub-section 4.1, No in-text citation of Eqn (2)

Line 214: move heading to new page 

Section 4.3, no in text citation of the Figure

Line 255: move heading to new page 

Line 256-264: No in text citation of the Figure 7 (a),…

Line 279: Number the Eqns correctly

Section 6.1, No in text citation of the “Eqn 3-5”

Subsection 6.2, no in-text citation of Figure 8 (a),…

Table 6 &7 is not cited

 The paper needs significant grammar improvements

Significant language editing must be done.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear authors,

The topic address the application area of fuel consumption prediction with use of neural networks. The main question is what is the best neural network model for forecasting fuel consumption with using jerk derivative of acceleration.

Novelty is in the application - use of neural networks with the third derivative of distance - jerk. The methodology is fine.

The conclusions consistent with the evidence and arguments presented and they address the main question posed.

The references are appropriate.

 - small corrections:

1. Double space on line 35.

2. Line 107 - unnecessary comma after e.g. in parenthesis.

3. Figure 1 caption should be on the page 3 under figure not on the next page.

4.  Unnecessary new line at line 133.

5. Line 201 - error in word behavior .

6. Figures on figure 8 should be bigger and of higher quality - the pictures are the summary of the neural networks errors.

General remark: all the diagrams should be bigger.

General comment:

The paper is very interesting and should be accepted with minor corrections above.

English is overall ok, there are small errors, more connected with editing,  described above.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Currently, the problem of predicting fuel consumption by vehicles is an urgent task. Taking into account the main operational factors, this reduces the energy consumption for moving the car. This task is relevant for both conventional and electric vehicles and hybrids.

There are several concepts for determining fuel consumption. The authors of the article consider well-known solutions based on the use of neural networks methodology. This approach has the right to exist, although it requires a high quality of empiricism and substantiation of input parameters.

As a remark, it requires a more detailed description of the objects of study, as well as a justification why only the parameters of the car's movement are considered and not, for example, the road profile.

Currently, the problem of predicting fuel consumption by vehicles is an urgent task. Taking into account the main operational factors, this reduces the energy consumption for moving the car. This task is relevant for both conventional and electric vehicles and hybrids.

There are several concepts for determining fuel consumption. The authors of the article consider well-known solutions based on the use of neural networks methodology. This approach has the right to exist, although it requires a high quality of empiricism and substantiation of input parameters.

As a remark, it requires a more detailed description of the objects of study, as well as a justification why only the parameters of the car's movement are considered and not, for example, the road profile.

Author Response

Please see the attachment.

Author Response File: Author Response.docx