Road Surface Classification Using a Deep Ensemble Network with Sensor Feature Selection
Round 1
Reviewer 1 Report
Tab. 4 - Importance weight for "Vertical acceleration of front right wheel" is equal to 0.0000. Please explain this as it looks strange, or correct if the value is wrong.
More information about design of experimental verification is necessary (photos of the road surfaces, information about test vehicle, etc).
While theoretical part is rather broad, the experimental part needs some enhancement.
Author Response
The authors are grateful for the kind review. We believe that the manuscript was improved based on your suggestions. The answer to the review can be found in the PDF file. Again, thank you very much for your comments.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The text is in general well written. Some minor mistakes are found, but very minor and can be fixed with a careful review. I liked the paper and I have just some minor comments to improve it before the final acceptance.
Please, refrain from using the first person, “we, our, us”, please prefer using third person or passive voice instead.
Please, state clearly the contributions for the paper in the introductory section.
I think Section 4.3 is a bit superficial. You could elaborate more in explaining the training phase.
In order to ensure reproducibility, I would ask the authors to elaborate more in the explanation of the experimental setup in Section 5.1. Please, provide more details so that other researchers can easily reproduce your experiments.
Directions for future work are missing in the conclusion. Please include at least a sentence about it.
Author Response
The authors are grateful for the kind review. We believe that the manuscript was improved based on your suggestions. The answer to the review can be found in the PDF file. Again, thank you very much for your comments.
Author Response File: Author Response.pdf
