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.
The required revisions have been made.
[# PeerJ Staff Note - this decision was reviewed and approved by Jun Chen, a PeerJ Section Editor covering this Section #]
It is appropriate to accept this article after the plots in the Figures are labelled.
All requested corrections have been carefully made. The article can be published in my opinion.
All requested corrections have been carefully made. The article can be published in my opinion.
All requested corrections have been carefully made. The article can be published in my opinion.
All requested corrections have been carefully made. The article can be published in my opinion.
The manuscript meets this journal's standards
The manuscript meets this journal's standards
The manuscript meets this journal's standards
The authors addressed all my comments. The paper can be accepted in the present form.
-
-
-
In particular, the experimental results and design should be discussed in detail and sufficiently discussed.
[# PeerJ Staff Note: It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors are in agreement that they are relevant and useful #]
[# PeerJ Staff Note: Please ensure that all review and editorial comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. #]
Your work is good, but there are many typos. The English of the article should be checked by an expert. I've marked some of the misspellings in the PDF. I added a comment. You must comply with the warnings. The abstract article is a little weak compared to its content. It should summarize the article in full. Shapes must be developed. All suggested citations should be included. There are too many repeated citations in the article. The article should be rearranged as incoming.
The Experimental Result section of the article is a bit weak compared to the other sections. This section is the heart of the article. This is the part that belongs to you. Therefore, this section should be developed. The resolution of the figures should be increased. The biggest shortcoming is that there is no confusion matrix. There are calculations, but there are no confusion matrices used to make these calculations. Add at least the confusion matrix of the model you propose (the most successful model, E-CNN). Include the ROC curve if possible. These will enable the reader to better understand and evaluate the article.
As stated in the previous comments, more detailed analysis is required to prove the validity of the findings.
Correct the article by considering the warnings and comments in the PDF uploaded to the system. Also take into account the comments made in general.
Figures' quality is not enough.
(For more detail, see attachments)
The methods, especially how the ensemble learning was applied in this study, was not explained in detail.
(For more detail, see attachments)
The experimental results (training length of networks) is not enough to compare methods.
It was not provided how many samples were used to compute the statistical p-values.
(For more detail, see attachments)
The motivation of this study is promising. However, it is not easy to make sure of the superiority of the proposed model with such short training.
The paper has some drawbacks:
1. The overview of the related papers should be expanded. It's a very popular research area. I suggest the authors evaluate these papers related to Transfer Learning and Ensemble Learning Techniques:
https://www.nature.com/articles/s41598-021-93783-8
https://ieeexplore.ieee.org/document/9107128
2. The presentation of Figures 7, 8 should be improved.
What image preprocessing technique do the author use?
The authors should present confusion matrices for each dataset.
The authors used only one dataset for testing and validation. It's not enough.
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.