Enhancing Autonomous Driving Safety: A Robust Stacking Ensemble Model for Traffic Sign Detection and Recognition

Round 1

Reviewer 1 Report (Previous Reviewer 1)

Comments and Suggestions for Authors

You stated in the Abstract that your proposition "exhibited enhanced performance". However, it should be added if competitive methods and the proposed methods used the same hardware/software configuration. It is not the same if computer are different. Clarify this in manuscript and Abstract text.  

Well, this journal deals more with economical aspects than as this technical details. I would rather see this paper in IEEE Access or in Applied Sciences than here. 

Author Response

Dear Reviewer,

Thank you for your insightful comments and suggestions on our manuscript. We have carefully considered each point and have made the necessary revisions to the manuscript. Below, we address your specific comments:

1. Regarding the performance comparison, we understand the importance of ensuring that the comparison is fair and based on the same hardware/software configuration. We have now clarified in the manuscript and the abstract that all methods were tested under the same conditions. 

2. We appreciate your feedback on the focus of our paper. While our work does delve into technical details, we believe it has significant economic implications that align with the scope of this journal. 

We have highlighted the changes made to the manuscript to make it easier for you and the editors to review. We have also included a cover letter that responds to each of your comments in detail.

Thank you again for your valuable feedback.

Author Response File: Author Response.docx

Reviewer 2 Report (Previous Reviewer 2)

Comments and Suggestions for Authors

The authors have addressed my comments.

Author Response

Dear Reviewer,

Thank you for your previous round of comments and suggestions on our manuscript. Although you did not provide additional comments in this round, we would like to express our gratitude for your valuable feedback in the previous review cycle. Your insights have significantly contributed to the improvement of our work.

We have carefully considered all previous comments and have made the necessary revisions to the manuscript. We believe that these changes have enhanced the clarity, rigor, and overall quality of our research.

Thank you once again for your time and effort in reviewing our manuscript. We hope that our revisions meet with your approval.

Author Response File: Author Response.docx

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

- I'm not sure that "Traffic Sign Detection" fits the aims of Sustainability. You should elaborate this in details in the manuscript. I suggest that you transfer the paper to closely related journal, because the paper is well and it would be important to be presented to appropriate readers (Journal of Imaging, Sensors, Electronics, Applied Sciences...).

- You must improve your references by adding published papers in relevant journals in 2023-24.

- You stated that your proposal is faster. Is it due to faster hardware configuration? To compare execution speed, you need to repeat experiments on the same hardware and software configuration for all considered methods.

- Regarding Figure 1: There is a block "Data processing and...". How did you process data? That should be explained in more details. How do you process external factors and what are they?

Reviewer 2 Report

Comments and Suggestions for Authors

This paper proposes and evaluates the combination of several vision recognition models for traffic sign recognition. I think the combination is not very novel, but the analyses are interesting. As the datasets have been used in previous papers, I miss a comparison to results reported in previous papers.

Comments to improve the paper:

·         In general, I think it is necessary to improve the quality of the figures and graph. I think the resolution is very low.

·         In section 3, when explaining the models, I’d appreciate some figures showing the architectures.

·         I miss a more detailed description of the datasets: number of images, how are they divided into training, validation and testing?

·         Figure 1 describes the training process, isn’t it?

·         The design of figure 2 makes difficult to understand the figure.

·         Table 1: some number of decimals.

·         Section 4: The new model improves the isolated models, but I miss a stronger comparison to previous works using these datasets.

·         I also suggest including any statistical significance analysis to see how the relevant are the differences between the systems (tables 2 and 3).

·         I’d suggest zooming up figure 4: lines and fonts.