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 May 23rd, 2024 and was peer-reviewed by 2 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on July 18th, 2024.
  • The first revision was submitted on August 9th, 2024 and was reviewed by 1 reviewer and the Academic Editor.
  • A further revision was submitted on September 17th, 2024 and was reviewed by 2 reviewers and the Academic Editor.
  • The article was Accepted by the Academic Editor on September 23rd, 2024.

Version 0.3 (accepted)

· Sep 23, 2024 · Academic Editor

Accept

Thanks to the authors for their efforts to improve the work. This version successfully satisfied the reviewers. It can be accepted currently. Congrats!

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

·

Basic reporting

My previous feedback has been addressed, and everything looks good now.

Experimental design

My previous feedback has been addressed, and everything looks good now.

Validity of the findings

My previous feedback has been addressed, and everything looks good now.

Additional comments

N/A

Reviewer 2 ·

Basic reporting

My comments have been addressed. It is acceptable in the present form.

Experimental design

My comments have been addressed. It is acceptable in the present form.

Validity of the findings

My comments have been addressed. It is acceptable in the present form.

Version 0.2

· Aug 16, 2024 · Academic Editor

Major Revisions

Thanks to the authors for their efforts to improve the work. However, the issues are only partially addressed. Please revise the article continually according to the comments.

Reviewer 2 ·

Basic reporting

The authors should thoroughly address the comments and make necessary improvements.

Experimental design

The authors should thoroughly address the comments and make necessary improvements.

Validity of the findings

The authors should thoroughly address the comments and make necessary improvements.

Additional comments

My prior comments that the authors still need to work further upon are listed below. I think the authors should also make some improvements in their updates.

1) The paper should place the proposed method in the context of state-of-the-art techniques, clearly delineating its advantages and limitations.

2) The methodology section lacks sufficient detail about the key steps involved in the proposed approach. Each step should be described in detail, with clear explanations and justifications.

3) The recursive sub-tensor compressive sensing algorithm is not explained clearly. The paper should provide a step-by-step description of the algorithm, including the mathematical formulation and theoretical underpinnings.

4) The criterion for determining the optimal band using spatial spectral decorrelation needs further clarification. The paper should explain how this criterion is computed and why it is effective.

5) The robustness of the proposed method should be tested under different conditions, such as varying sampling rates and different types of HSIs.

Version 0.1 (original submission)

· Jul 18, 2024 · Academic Editor

Major Revisions

Please revise the article according to the comments of the reviewers. Then it will be evaluated again.

·

Basic reporting

1. The paper is well structured and has a clear introduction, methods, results, and discussion sections. However, one thing is missing - the paper should discuss the potential limitations of the proposed method and suggest areas for future research.

2. It is better to have more recent references to highlight the current state of research in this field. Most of the current references are before 2020.

Experimental design

1. While the experimental procedure is clear to me, I think there could be more description of the data source. How are those leaves being picked? Any preprocessing step is being done?

2. The discussion about reproducibility seems missing.

3. The evaluation could be further proved by introducing additional performance metrics like structural similarity index etc.

Validity of the findings

1. The paper does not discuss the computational complexity and runtime of the RSTHCS method compared to other approaches. This can be further discussed.

2. The method is currently evaluated only on tea leaves and soybean leaves. We can expand to a wider range of plant species and leaf types to prove the evaluation in a larger scope.

Additional comments

N/A

Reviewer 2 ·

Basic reporting

The manuscript entitled “A Novel Recursive Sub-Tensor Hyperspectral Compressive Sensing of Plant Leaves Based on Multiple Arbitrary-Shape Regions of Interest” has been investigated in detail. The paper proposes a novel method for compressing hyperspectral images (HSIs) of plant leaves by focusing on the relevant leaf regions and discarding background information, which aims to improve storage efficiency and reconstruction quality. While the approach is interesting and has potential benefits, the paper suffers from several significant issues that need to be addressed for it to meet the standards of scientific rigor and clarity.
1) The introduction does not clearly define the problem of HSI compression and the specific challenges that the proposed method addresses. A detailed problem statement is necessary to contextualize the research.
2) The motivation for choosing recursive sub-tensor compressive sensing over existing methods is not well articulated. The paper should provide a stronger rationale for the proposed approach.
3) The literature review is inadequate, failing to cover a comprehensive range of existing methods in hyperspectral image compression. A thorough review of related works is needed to highlight the novelty and significance of the proposed method.
4) The paper should place the proposed method in the context of state-of-the-art techniques, clearly delineating its advantages and limitations.

Experimental design

5) The methodology section lacks sufficient detail about the key steps involved in the proposed approach. Each step should be described in detail, with clear explanations and justifications.
6) The recursive sub-tensor compressive sensing algorithm is not explained clearly. The paper should provide a step-by-step description of the algorithm, including the mathematical formulation and theoretical underpinnings.
7) The criterion for determining the optimal band using spatial spectral decorrelation needs further clarification. The paper should explain how this criterion is computed and why it is effective.
8) The choice of performance metrics (e.g., PSNR, SAM, spectral indices) should be justified. The paper should explain why these metrics are appropriate for evaluating the proposed method.

Validity of the findings

9) The robustness of the proposed method should be tested under different conditions, such as varying sampling rates and different types of HSIs.
10) “Discussion” section should be edited in a more highlighting, argumentative way. The author should analysis the reason why the tested results is achieved.
11) The authors should clearly emphasize the contribution of the study. Please note that the up-to-date of references will contribute to the up-to-date of your manuscript. The studies named- “Artificial intelligence-based robust hybrid algorithm design and implementation for real-time detection of plant diseases in agricultural environments; Agricultural crop classification with R-CNN and machine learning methods” - can be used to explain the methodology in the study or to indicate the contribution in the “Introduction” section.
This study may be proposed for publication if it is addressed in the specified problems.

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.