Review History


All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.

Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.

View examples of open peer review.

Summary

  • The initial submission of this article was received on October 11th, 2022 and was peer-reviewed by 2 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on November 15th, 2022.
  • The first revision was submitted on December 14th, 2022 and was reviewed by 2 reviewers and the Academic Editor.
  • The article was Accepted by the Academic Editor on December 28th, 2022.

Version 0.2 (accepted)

· Dec 28, 2022 · Academic Editor

Accept

Thank you for the hard work in order to clearly and appropriately address all of the reviewers' comments.

[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a PeerJ Computer Science Section Editor covering this Section #]

Reviewer 1 ·

Basic reporting

Overall this version has improved a lot and no further comments.

Experimental design

no comment

Validity of the findings

no comment

Additional comments

no comment

·

Basic reporting

The revised verison has been improved. The revised paper is well written in general.

Experimental design

The authors have provided extended discussions and detials for the experiments. My previous concerns have been addressed.

Validity of the findings

The revised paper has been improved. Validity of the results are futher improved by discussions on the results.

Additional comments

My previous concerns have been addressed.

Version 0.1 (original submission)

· Nov 15, 2022 · Academic Editor

Major Revisions

Dear authors, we strongly advise you to respond to the comments, concerns, and questions raised by reviewers (especially the second reviewer), which are listed at the bottom of this letter, and then resubmit your paper once it has been revised.

[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]

Reviewer 1 ·

Basic reporting

1. The overall English quality is not satisfactory.
2. The research background is not enough, with only very limited references for roof type classification. The flaws of the existing roof type classification methods and the advantages of Siamese Neural Networks for similar problems are not summarized. The research gap and the research motivation for proposing a new machine learning based on Siamese Neural Network is not clear.
3. The figures are in a low quality.

Experimental design

1. The knowledge gap is not identified. The research design with two datasets and the usage of artificial data set instead of real-world data set is not justified.
2. The model details for both the DenseNet CNN model and the SNN model are not given, making the results less reliable.
3. There are more recent solutions for computer vision problems, and the choice of the SNN structure as the solution and the choice of DenseNet as the baseline are not so convincing.

Validity of the findings

1. The datasets are publicly available, but the replication is not possible since the source code is not provided.

·

Basic reporting

This paper is well written in general. The methodology is sound and the ideas are interesting to readers.

The authors studied the roof type image classification, with special interests in the application of Siamese network.

The authors proposed a method based on one shot training is investigated and large amount of training data is avoided. The literature review could be futher enhanced, more recent work within three years could be included and compared. Such as some new studies on Siamese network and their applications in retail image classificaion, remote sensing, etc.

Experimental design

Is the dataset used in this study public available, and where can the readers obtain such dataset used in the experiments?
DenseNet and other backbone architectures are discussed in this paper, I would suggest to more discussion on why the authors choose the specific network structure in the experiments.

The details of parameter settings for their experiments could be further provided for the interested readers to reproduce and compare the results.

Validity of the findings

The conlusion is supported by the experimental results.

All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.