PONE-D-24-58741Flexi-YOLO: A Lightweight Method for Road Crack Detection in Complex EnvironmentsPLOS ONE

Dear Dr. Yang,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Mar 10 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Peng Geng

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at 

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager.

3. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

4. Thank you for stating the following financial disclosure: 

This work was supported by the National Natural Science Foundation of China under Grants (62276034、62306052), Group Building Scientific Innovation Project for Universities in Chongqing (CXQT21021), Joint Training Base Construction Project for Graduate Students in Chongqing (JDLHPYJD2021016), and Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN202100712).  

Please state what role the funders took in the study.  If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."" 

If this statement is not correct you must amend it as needed. 

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

5. We note that your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files.

Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition).

For example, authors should submit the following data:

- The values behind the means, standard deviations and other measures reported;

- The values used to build graphs;

- The points extracted from images for analysis.

Authors do not need to submit their entire data set if only a portion of the data was used in the reported study.

If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories.

If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access. 

6. We are unable to open your Supporting Information file Flexi-YOLO.tex. Please kindly revise as necessary and re-upload.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Language Correction:

Abstract:

Rephrase for conciseness and impact. For instance:

"Road crack detection is vital for infrastructure maintenance and public safety, yet complex backgrounds and irregular crack shapes challenge real-time, efficient, and accurate detection. This paper proposes Flexi-YOLO, a lightweight and robust model based on YOLOv8, incorporating novel components to address these challenges. Key innovations include the Wise-IoU loss function for enhanced regression accuracy and robustness, the DCNv-C2f module for feature transformation, and the Global Attention Module (GAM) for improved global information perception. Flexi-YOLO achieves significant improvements in accuracy, recall, and mAP metrics, offering a cost-effective solution for automated crack detection."

Introduction:

Rewrite to engage the reader and highlight the importance of the work globally, not just in a single country. Example:

"Road networks form the backbone of global infrastructure, critical to economic growth and societal well-being. However, environmental stressors and prolonged usage lead to structural deterioration, with cracks posing risks to safety, durability, and usability. Timely and accurate crack detection is essential to mitigate these issues, reduce maintenance costs, and ensure sustainability. This paper addresses these challenges by proposing an innovative, lightweight model tailored for real-time crack detection in diverse and complex environments."

Related Work:

Ensure smooth transitions between traditional methods and deep learning advancements.

Expand on limitations of existing YOLO-based methods and how Flexi-YOLO surpasses them.

Methodology:

Clarify technical terms like “Wise-IoU,” “G-Head,” and “AKConv” with succinct explanations. Avoid jargon overload.

More Literature Review:

Discuss advancements in deep learning for infrastructure health monitoring, such as applications beyond road cracks (e.g., bridge, pipeline, and building inspections).

Include recent works utilizing YOLO-based architectures in different domains to position Flexi-YOLO in the broader context.

Highlight shortcomings of current methods, like high computational requirements, sensitivity to noise, or lack of adaptability to varying crack shapes.

Incorporate examples of lightweight models applied in mobile and edge computing for infrastructure maintenance, emphasizing how Flexi-YOLO aligns with these trends.

You can follow

[1] S. Mandal, A. Shiuly, D. Sau, A. K. Mondal, and K. Sarkar, “Study on the use of different machine learning techniques for prediction of concrete properties from their mixture proportions with their deterministic and robust optimisation,” AI Civ. Eng., vol. 3, no. 1, p. 7, Dec. 2024, doi: 10.1007/s43503-024-00024-8.

[2] K. Sarkar, A. Shiuly, and K. G. Dhal, “Revolutionizing concrete analysis: An in-depth survey of AI-powered insights with image-centric approaches on comprehensive quality control, advanced crack detection and concrete property exploration,” Constr. Build. Mater., vol. 411, p. 134212, Jan. 2024, doi: 10.1016/j.conbuildmat.2023.134212.

[3] A. Shiuly, D. Dutta, and A. Mondal, “Assessing compressive strengths of mortar and concrete from digital images by machine learning techniques,” Front. Struct. Civ. Eng., vol. 16, no. 3, pp. 347–358, Mar. 2022, doi: 10.1007/s11709-022-0819-z.

Highlighting the Novelty of the Work:

Clearly articulate the novel aspects of Flexi-YOLO in the introduction and conclusion. For example:

*"Flexi-YOLO introduces several novel contributions to road crack detection:

The integration of deformable convolution (DCNv3) in the C2f module enhances feature extraction for cracks with irregular shapes.

Variable kernel convolution (AKConv) dynamically adjusts to complex geometries, strengthening local feature representation.

A lightweight detection head (G-Head) reduces computational costs while preserving accuracy, making the model suitable for deployment on mobile devices.

Wise-IoU optimizes bounding box regression, improving robustness against low-quality samples.

These advancements collectively enhance detection accuracy, speed, and adaptability in diverse environments."*

Presenting the Objectives:

The objectives should be clearly stated at the end of the introduction. Example:

*"This work aims to address the challenges of road crack detection by achieving the following objectives:

Develop a lightweight and efficient model suitable for deployment on devices with limited computational power.

Enhance feature extraction for complex crack geometries using deformable convolution and variable kernel techniques.

Improve detection robustness and accuracy with a novel loss function and attention mechanisms.

Reduce feature redundancy and computational load through a redesigned detection head, ensuring real-time performance.

Validate the model's performance in diverse, real-world scenarios to meet industrial demands."*

Language Refinement:

Avoid repetitive phrases like "complex backgrounds" and "irregular crack shapes." Use synonyms or restructure sentences for variety.

Use active voice for clarity and engagement. For example:

"Flexi-YOLO addresses the limitations of previous methods by leveraging advanced convolutional techniques and attention mechanisms."

Conclusion:

Reiterate the novelty and potential applications of Flexi-YOLO, emphasizing its real-world impact. Example:

"Flexi-YOLO represents a significant step forward in automated road crack detection. Its lightweight design, coupled with state-of-the-art feature extraction and attention mechanisms, ensures high accuracy and adaptability in diverse environments. This model not only meets the demands of real-time applications but also offers a cost-effective solution for infrastructure maintenance, contributing to public safety and sustainability."

These revisions will make the paper more cohesive, engaging, and aligned with high-quality academic standards. Let me know if you'd like further assistance!

· Major Findings:

Highlighted the key advancements and methodologies that contribute to the subject matter.

Identified critical gaps in the current knowledge and addressed them through detailed analysis.

Proposed actionable solutions and models that demonstrate tangible benefits for the stakeholders.

· Backlog of Present Study:

While the study successfully explored its core objectives, certain aspects remain for future exploration, including:

Incorporating broader datasets to improve the generalizability of the findings.

Addressing region-specific challenges that require further analysis.

Testing the proposed solutions in real-world scenarios to evaluate long-term impact.

· Overall Benefits:

The study provides significant insights and practical recommendations that:

Enhance understanding and inform decision-making in the relevant domain.

Lay the groundwork for sustainable practices and innovative applications.

Foster collaboration and drive further research to achieve long-term goals.

Reviewer #2: The paper presents Flexi-YOLO, an enhanced road crack detection model based on YOLOv8, which improves detection accuracy while maintaining a lightweight design. The manuscript is generally well-structured and contributes valuable insights to the field of road crack detection. However, there are several important issues that need to be addressed before the paper can be accepted and published:

1.The dataset used in the study contains 4,040 images with predefined augmentation techniques. This may limit the model's ability to generalize to diverse road conditions and surface types in real-world applications. A broader, more varied dataset could improve the model’s adaptability across different environments.

2.While the model demonstrates strong performance in controlled experiments, there is a lack of real-world validation to assess its robustness under different environmental conditions (e.g., varying lighting, weather, and road types). It is crucial to test the model in non-controlled, field-based scenarios to ensure its practical applicability.

3.Despite the focus on a lightweight model, the experimental setup relies on high-performance hardware such as the NVIDIA RTX 4090 GPU. This contradicts the paper’s claim of low computational cost, especially for deployment in mobile or resource-constrained environments. It would be helpful to see performance metrics on more typical, low-cost hardware configurations.

4.The paper compares the Flexi-YOLO model with YOLOv5, YOLOv7, and YOLOv8, but it does not include other state-of-the-art lightweight models (e.g., transformer-based models or more recent, efficient architectures). Including a broader range of models for comparison would provide a more comprehensive evaluation of the Flexi-YOLO model’s performance and efficiency.

5.The authors use several image augmentation techniques to improve model robustness. It would be beneficial to briefly discuss how these augmentation methods specifically influence the model’s performance, particularly for detecting cracks under varying conditions (e.g., different weather, lighting, and road types). A deeper analysis of the role and effectiveness of these augmentation strategies would offer valuable insights into how the model generalizes across real-world scenarios. For example, the ideas in these paper can be used as a reference:1.Automatic detection of tunnel lining crack based on mobile image acquisition system and deep learning ensemble model. https://doi.org/10.1016/j.tust.2024.106124. 2. Tunnel lining crack detection model based on improved YOLOv5. https://doi.org/10.1016/j.tust.2024.105713

The paper introduces several advanced techniques (e.g., GAM, AKConv) to enhance detection accuracy. However, it would be helpful to include a brief discussion on the interpretability of the model. How can users or practitioners understand and interpret the decisions made by the model, especially in edge cases where false positives or negatives occur? Providing insight into the model’s decision-making process could enhance its acceptance in real-world applications.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

PONE-D-24-58741R1Flexi-YOLO : A Lightweight Method for Road Crack Detection in Complex EnvironmentsPLOS ONE

Dear Dr. Yang,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by May 24 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Peng Geng

Academic Editor

PLOS ONE

Additional Editor Comments (if provided):

It is recommended that authors carefully revise according to the reviewer's suggestions, otherwise the reviewer may not approve it.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: (No Response)

Reviewer #2: All comments have been addressed

Reviewer #3: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Yes

Reviewer #3: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: No

Reviewer #2: Yes

Reviewer #3: N/A

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: No

Reviewer #2: Yes

Reviewer #3: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Please see carefully the comments and give reply. All the comments are not answered satisfactorily.Literature review should be strengthened and find the critical gap of literature.

10.1016/j.conbuildmat.2023.134212

10.1007/s11709-022-0819-z

Reviewer #2: I don't have any other comments. My suggestions have been fully considered and the article has met the requirements for publication.

Reviewer #3: The manuscript presents Flexi-YOLO, a lightweight architecture based on YOLOv8 specifically for road crack detection in complex and resource-constrained environments. The authors innovatively combined several advanced techniques to enhance detection accuracy while ensuring computational efficiency suitable for edge devices. The manuscript is generally well-structured, rich in methodological details, and complemented by thorough experiments. The authors not only clearly described data preprocessing methods but also explicitly defined the performance metrics, providing associated formulas, and presented results with abundant diagrams and tables that assists readers in interpreting the robustness and reliability of the proposed method and findings. However, there are still some improvements to further increase the academic rigor of the paper.

Minor comments

1. Please provide clear links and/or references to the source dataset Roboflow crack dataset for full credibility and reproducibility.

2. The section of “Model Generalization Experiment”, on page 24, is considerate and well-executed, however, adding additional details about the class distribution within the datasets would be helpful.

3. The section of “Computational Analysis of Low-Power Devices”, on page 26 and 27, mentions good performance on hardware test. Could you expand this section by including quantitative metrics such as power consumption, latency during inference, memory consumption, and frames per second? This guarantees the sustainability and suitability for edge deployment.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: Yes: Amit Shiuly

Reviewer #2: No

Reviewer #3: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Flexi-YOLO : A Lightweight Method for Road Crack Detection in Complex Environments

PONE-D-24-58741R2

Dear Dr. Yang,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Peng Geng

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #3: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #3: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #3: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #3: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #3: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: As the authors have addressed all the comments and concerns raised during the review process satisfactorily, I find no remaining issues. The manuscript meets the necessary standards and can be accepted for publication. I have no concerns regarding dual publication, research ethics, or publication ethics.

Reviewer #3: Thanks the authors for meticulously addressing my comments around providing more concrete quantitative metrics for the model performance, describing data distributions in the dataset, and including links/references to the dataset. I think the current manuscript is ready for publication.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: Yes: Amit Shiuly

Reviewer #3: No

**********