PONE-D-25-30171Enhancing Reliability in Electrical Grids: A Hybrid Machine Learning Approach for Electrical Faults ClassificationPLOS ONE

Dear Dr. Uddin,

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 Sep 15 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,

Haris Calgan, Ph.D.

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. Thank you for stating the following financial disclosure:

“This research was funded by Multimedia University, Cyberjaya, Selangor, Malaysia

(Grant Number: PostDoc (MMUI/240029)).”

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.

3. Please note that your Data Availability Statement is currently missing the repository name. If your manuscript is accepted for publication, you will be asked to provide these details on a very short timeline. We therefore suggest that you provide this information now, though we will not hold up the peer review process if you are unable.

4. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

5. We note you have included a table to which you do not refer in the text of your manuscript. Please ensure that you refer to Table 1 in your text; if accepted, production will need this reference to link the reader to the Table.

6. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Additional Editor Comments:

Enclosed please find detailed reviewer reports on the paper that you have submitted for possible publication in the PLOS ONE.

The reviewers require a MAJOR REVISION of your paper.

If you are prepared to undertake the work required, I would be pleased to reconsider my decision. However, I would like to ask you to very carefully address the issues raised by the reviewers and revise your paper accordingly.

Please keep in mind that if citation suggestions have been made by reviewers, these suggestions are optional and will not influence the editor's decision. Do not include citations that are irrelevant to the paper or that you believe will not add value to the manuscript.

[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: Partly

Reviewer #2: No

Reviewer #3: Partly

Reviewer #4: Yes

Reviewer #5: Partly

**********

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

Reviewer #1: No

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: N/A

Reviewer #5: I Don't Know

**********

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: No

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: 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: No

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: No

**********

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: 1. The paper lacks in major contribution and motivation of research.

2. The background and significance of this study should be highlighted in the abstract.

3. Check the English presentation of this paper to remove the typo mistakes. Some grammatical issues need to be addressed in the whole text. Please reform the long paragraphs. Please polish the writing and English of the manuscript carefully. The writing of the paper needs a lot of improvement in terms of grammar, spelling, and presentation. The paper needs careful English polishing since there are many typos and poorly written sentences. I found several errors.

4. In the "Introduction" section, a more detailed analysis of the existing literature on the subject is needed, and an in-depth analysis of the possible application fields.

5. The mathematics used throughout the article is still not very strict. Please try to update and illustrate some elements in the mathematical model that are not defined very strictly.

6. The overall structure of the article should be improved.

7. The result part is week, results and discussion should be better explained.

8. References must be updated and add the suitable from the following

https://doi.org/10.3390/en12050961, https://doi.org/10.1109/EIConRus.2018.8317170, https://doi.org/10.1016/j.est.2024.113556, https://doi.org/10.1109/ACCESS.2024.3437191, https://doi.org/10.1109/MEPCON.2017.8301313, https://dx.doi.org/10.21608/jaet.2021.82231, https://doi.org/10.1109/MEPCON47431.2019.9008171, https://doi.org/10.21608/sej.2021.155557,

https://doi.org/10.1109/MEPCON58725.2023.10462371, DOI: 10.1109/ACCESS.2024.3525183, https://doi.org/10.1007/s00521-024-09433-3, https://doi.org/10.1371/journal.pone.0317619, https://doi.org/10.20508/ijrer.v14i2.14346.g8898, https://doi.org/10.20508/ijrer.v13i1.13718.g8659, https://doi.org/10.1007/s00521-024-09433-3, https://doi.org/10.1007/s00521-024-09902-9, https://doi.org/10.21608/SVUSRC.2024.279389.1198,

9. Check all of your Figures and Tables have a good explanation of your text.

10. Many paragraphs without citations

11. What are the contributions and novelty of work mentioned?

12. The authors' conclusions need to be improved, a comparison of the results obtained with those already existing in the literature would be appropriate. I suggest also describing what can still be improved in this work, which can still be improved based on the results obtained, according to the authors' view. It is suggested to offer some limitations existed in this study and an outlook for future study in the last section.

Reviewer #2: The manuscript presents a hybrid machine learning model for fault classification in electrical transmission lines using a combination of RF, DT, and stacking techniques. However, the proposed approach lacks novelty, relies heavily on standard methods, and does not provide sufficient technical rigor or validation to justify publication. The paper also fails to engage with recent literature and presents overstated contributions without empirical support.

Reviewer Comments:

1.The hybrid ensemble model proposed in this work (RF + DT + Gradient Boosting) is a routine ML pipeline with no algorithmic innovation or novel architecture. Similar stacking-based models have already been widely reported in existing literature.

2.The dataset used is publicly available and small in scale, with no cross-validation, statistical tests, or robustness analysis. This undermines the reliability and generalizability of the reported 93.64% accuracy.

3.References are outdated and do not include any recent (2023–2025) high-impact studies using advanced techniques such as deep learning, GNNs, or explainable AI in power systems. This severely limits the relevance of the work.

4.Many sections are filled with textbook-level explanations of basic ML algorithms (e.g., Naive Bayes, KNN), which do not contribute to the research and make the manuscript overly lengthy without adding scientific value.

5.The manuscript lacks real-world validation on standard IEEE test systems, and key aspects such as model interpretability, class-wise performance, and computational feasibility in grid environments are not addressed.

Reviewer #3: This is a solid and well-written paper that adds to the body of knowledge about how to use machine learning to identify faults in power systems. The design of the experiment is strong, the results are shown, and the open data/code policy makes it easier to reproduce the results.

The paper says that the hybrid model is new; however, other research has used similar stacking ensembles to find faults (see [15], [16], and [22]). The exact combo of RF+DT+GB works, but it isn't really new.

There is a difference in the stated accuracy. The abstract and Section 4.2 say 93.64%, whereas Table 5 shows 94% for Model-1 with Stacking (GB), and Table 6 includes 93.64% and 99.58% (binary example).

Section 5 of the discussion says, "Our proposed work achieves about 94% accuracy, which is a little lower than the other methods shown in the literature." Table 6, on the other hand, demonstrates that some earlier works had better accuracy (98–99.93%).

The report says that GB was chosen over linear regression because it worked better; however, it doesn't show LR's results for comparison.

The dataset comes from Kaggle [35], but there are no details on how the data was created (simulation, real-world, lab setting), the sampling rate, or feature engineering.

Table 4 shows execution time and memory, but the text doesn't talk about how it can be used in real time.

A cognitive science definition of "blending" is given first, which is not useful in the context of ML.

Figure 4 Please put "Accuracy" on the y-axis and make sure that all the numbers match those in Table 5.

Equations, Make sure the formatting is the same throughout (for example, Equation 14 uses f(x) and f^(x), but the text uses y^).

Table 6, To make the contrast between 6 classes and 2 classes clearer, add a column for "Fault Classes."

In the abstract, don't list all of the machine learning algorithms; just say "various machine learning algorithms."

Conclusion: Don't rehash the results; instead, the conclusion should bring together the implications.

Reviewer #4: The answers to the questions above and the issues requiring further clarification and improvement in the paper:

1.Technical Soundness & Conclusion Support (Q1: Yes)

The manuscript presents a technically sound study, and the experimental/data analysis methods are appropriate for addressing the research question. The conclusions are supported by the results. However, In order to further strengthen the conclusion that the proposed hybrid model is effective for electrical fault classification tasks, I suggest to conduct a comparative analysis of the four evaluation indexes in the discussion section.

2.Statistical Analysis (Q2: N/A)

The question regarding statistical analysis is marked as 'N/A' because this study focuses on evaluating the performance of a hybrid machine learning model for fault diagnosis, where the results are primarily validated through computational metrics (e.g., accuracy, precision, F1-score) rather than traditional statistical hypothesis testing. If the authors employed any statistical methods (e.g., significance testing of model comparisons), these should be explicitly stated in the Methods section.

3.Data Availability (Q3: Yes)

The manuscript utilizes publicly available data from the Electrical Faults Analysis & Classification dataset, and the source is appropriately cited in Section 3.1. If the database requires specific licensing statements, these should be added.

4.Language & Clarity (Q4: Yes)

This paper is written in standard English and has a relatively clear logical structure. However, some parts of Algorithm 1 and 4.1 need to be appropriately explained and adjusted according to the overall research ideas of the paper.

5.Model combination strategy lacks comprehensiveness

The authors selected DT and RF for combination based solely on their individual performance. While this approach is intuitive, it lacks a systematic evaluation of all possible model pairs. Other combinations (such as SVM and NB) may provide complementary strengths that lead to better hybrid performance. I suggest including comparative experiments on all pairwise model combinations to ensure the selected hybrid model is indeed optimal.

6.Model selection rationale needs further justification

Although the study focuses on A,P,R,F1, execution time and memory usage are also reported but not analyzed. If the hybrid of DT and RF is not the best in terms of time and memory consumption, the rationale behind choosing this pair should be elaborated. For example, is model interpretability, robustness, or ease of deployment a contributing factor? Currently, the reasoning appears somewhat incomplete.

7.Fairness of Comparative Experiments

It is recommended that the authors clarify whether all models were evaluated under

consistent experimental conditions—such as using the same training/testing splits and comparable hyperparameter optimization strategies. Ensuring uniform settings is essential for a fair and valid comparison of model performance.

8.Generalizability of the Hybrid Approach

The current hybrid modeling strategy may be tailored to the specific characteristics of the

dataset or fault type used in this study. The authors are encouraged to discuss whether the proposed method is generalizable to other fault diagnosis scenarios or industrial datasets, and to specify any potential limitations regarding its applicability.

9. manuscript structure

The evaluation metrics (e.g.,accuracy, precision, recall, F1-score�Equations (15)-(17)) are currently introduced and defined in Section 4.1. However, these metrics are integral to the methodology and should ideally be presented earlier in the paper—preferably in the section describing the diagnostic framework or evaluation methodology. This would improve the logical flow of the manuscript.

Reviewer #5: One of the consequences of the power systems complexity increasing consists in the rise of probability of system fault occurrence. A rapid restoration of power system enhances the service reliability and reduces power outages; therefore, fault section should be estimated quickly and accurately. To guarantee the reliability and safety of a power system, efficient fault detection, classification, and localization (FDL) is essential. Consequently, the improvement in suitable techniques for the fault detection, classification and localization in power systems, to increase the efficiency of the systems and to avoid major damages, it is a permanent requirement.

These advanced fault classification techniques turn to AI-based methods, or to a series of other modern techniques already developed, implemented, and used in power systems (for analysis, monitoring, control, etc.).

The relevance of the article is not convincing. The reviewer trusts the following comments can help the authors to improve the quality of their work:

1. The presentation of the research in the form of questions and answers is not the most appropriate for such an article.

2. All paragraphs and subparagraphs should be numbered in order starting with “1. Introduction” etc.

3. The article should begin with the following statement: “Transmission lines are critical components of modern electricity distribution networks, enabling the efficient transfer of electrical energy across vast geographical areas.” The definitions for “transmission lines” and “distribution networks” should be revised.

4. All tables and figures inserted in the paper should be referenced in the text before they appear (Table 4, Table 5). For example, Table 1 is not referenced at all in the text.

5. “Figure 2 shows the importance of each feature. The dataset includes data on different types of electrical faults, each characterized by a unique combination of outputs.” Explain why there are differences in the importance of different features? To what particular quantity is the quantity on the ordinate axis called “Importance” reported/referred?

6. “Table 2. Fault Types and their Corresponding Output Representations

This classification framework allows for accurate and efficient identification of six distinct types of faults, essential for effective fault detection and maintenance planning in electrical power systems.”

6.1. Why is the normal “No-Fault” regime treated as a “Type fault” fault regime?

6.3. What is the situation of other faults, for example:

- Phase B to Ground or phase C to ground;

- Between Phase A and Phase C, or between Phase B and Phase C, etc.

Table 2 needs to be reviewed.

7. Why is LLLG Fault a Three-phase symmetrical fault, but LLL Fault is a fault Between all three phases!?

8. The definition of the quantities A, R, P, F1 that appear in tables 4 and 5 must be presented before their use.

9. All equations present in the paper must be numbered in order: there are 2 equations (between equation 13 and 14) that are not numbered.

10. All quantities that appear in relations (14), (15), (16) and (17) must be identified/defined. For example: TPi, FPi, FNi, F1i!

11. Relations (15), (16), (17) are confusing! Does the quantity qi multiply the entire sum or each term of the sum? A few parentheses would help in this case.

12. The article is presented as an application of AI techniques for classifying faults in electrical networks. The specifics of this application related to fault classification do not result from the presentation. Therefore, in order to make a more accurate assessment, it should be specified:

- what is the structure of the electrical network analyzed with the basic data;

- what is the input data set and how was it obtained – if it was obtained through simulations, how was it performed, etc.

13. The article presents an algorithm “Algorithm 1” which leads to the conclusion that several algorithms were used. What are they?

14. The article contains too many paragraphs. These could be concentrated especially since they are repeated issues. For example, in 6 it appears “This model combines RF and DT algorithms with the Stacking technique (GB) to provide robust and accurate fault classification” and in 7: “This research offers a robust hybrid ML model combining RF, DT, and Stacking techniques, significantly improving fault classification accuracy.”

15. The references could be improved taking into account the fact that in recent times a significant number of works in the field have appeared.

**********

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

Reviewer #3: No

Reviewer #4: No

Reviewer #5: 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-25-30171R1Enhancing Reliability in Electrical Grids: A Hybrid Machine Learning Approach for Electrical Faults ClassificationPLOS ONE

Dear Dr. Uddin,

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.

==============================

ACADEMIC EDITOR: Please take into consideration the concerns of Reviewer #5.

==============================

Please submit your revised manuscript by Jan 01 2026 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,

Haris Calgan, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

[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: All comments have been addressed

Reviewer #3: All comments have been addressed

Reviewer #4: All comments have been addressed

Reviewer #5: (No Response)

**********

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

Reviewer #4: Yes

Reviewer #5: No

**********

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

Reviewer #1: Yes

Reviewer #3: Yes

Reviewer #4: N/A

Reviewer #5: I Don't Know

**********

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

Reviewer #4: Yes

Reviewer #5: 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

Reviewer #4: Yes

Reviewer #5: 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: authors made the required comments. So this manuscript is accepted for publications. it is accepted.

Reviewer #3: The authors have well answered and solved the comments raised for the first submission. The paper is of high quality and is now ready for publishing.

Reviewer #4: The author carefully replied to the reviewers' comments point by point and made significant modifications and improvements to the paper. The revised paper has obvious improvements in content structure, logical expression, and experimental verification, and basically solved the problems raised in the first review.

Reviewer #5: The authors should clarify the following aspects:

1. The title of the paper suggests that the research is focused on “Electrical Faults Classification”, but in the Introduction the authors state the following:

“This paper investigates the following key research questions:

• RQ1: What machine learning algorithms have been utilized for electrical fault detection, and what advantages do they offer in terms of accuracy, efficiency, and real-time fault diagnosis?

• RQ2: What novel methodology or framework is introduced in this study, and how does it enhance fault detection performance?

• RQ3: Which hybrid machine learning model can outperform previous research and improve the accuracy of electrical fault classification?”

These three questions suggest that the issues related to fault regimes in electrical networks: detection, classification, localization, and diagnosis of faults in electrical networks have the same significance.

What is the position of the authors in this regard? Does the paper address and answer all these issues?

2. The authors have incompletely answered, or have avoided answering, some questions raised in previous reviews, especially related to the specifics of the application - which distinguishes it from other ML applications - otherwise the algorithm can be applied to any data set, etc.

**********

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: No

Reviewer #3: No

Reviewer #4: No

Reviewer #5: 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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

PONE-D-25-30171R2Enhancing Reliability in Electrical Grids: A Hybrid Machine Learning Approach for Electrical Faults ClassificationPLOS One

Dear Dr. Uddin,

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.

==============================

ACADEMIC EDITOR:

The manuscript has improved substantially after the second revision. Several important reviewer and editorial concerns have been addressed. However, a few methodological and interpretational issues still require clarification before final acceptance.

Please see my comments below.

==============================

Please submit your revised manuscript by Feb 11 2026 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 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,

Haris Calgan, Ph.D.

Academic Editor

PLOS One

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

Additional Editor Comments:

The manuscript has improved substantially after the second revision. Several important reviewer and editorial concerns have been addressed. However, a few methodological and interpretational issues still require clarification before final acceptance.

-The claims regarding novelty have been moderated compared to the previous version, which is appreciated. Nevertheless, some statements still imply methodological novelty (e.g., references to a “novel methodology”). Please further clarify that the contribution is application-oriented, focusing on benchmarking, interpretability, and computational efficiency rather than algorithmic innovation.

- The study still does not include cross-validation (e.g., k-fold CV), robustness analysis, or statistical significance testing. While execution time and memory usage have been added, these do not substitute for proper validation. Please explicitly acknowledge this limitation in the manuscript and avoid claims that may suggest strong generalization performance.

-The discussion on real-time feasibility and computational efficiency has improved. However, the absence of validation on IEEE test systems or real-world data remains a limitation. Please ensure that claims regarding practical deployment are carefully qualified and framed as prospective rather than demonstrated.

- Please avoid overemphasizing the numerical accuracy values and refrain from using language that implies state-of-the-art performance. The reported accuracy (93.64% for six-class classification) is lower than several deep learning-based methods cited in the literature. he discussion should more clearly emphasize the trade-off between accuracy, interpretability, and computational efficiency.

The manuscript is close to being suitable for publication. Minor revisions are still required, primarily related to contribution framing and validation transparency. Addressing the above points will significantly strengthen the clarity and credibility of the work.

[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 #5: 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 #5: Yes

**********

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

Reviewer #5: I Don't Know

**********

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 #5: 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 #5: 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 #5: The article, with the changes made as a result of the reviewers' comments, appears in a form acceptable 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 #5: 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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Enhancing Reliability in Electrical Grids: A Hybrid Machine Learning Approach for Electrical Faults Classification

PONE-D-25-30171R3

Dear Dr. Uddin,

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. For questions related to billing, please contact billing support.

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,

Haris Calgan, Ph.D.

Academic Editor

PLOS One

Additional Editor Comments (optional):

Reviewers' comments: