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 March 22nd, 2024 and was peer-reviewed by 2 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on April 30th, 2024.
  • The first revision was submitted on June 5th, 2024 and was reviewed by the Academic Editor.
  • The article was Accepted by the Academic Editor on June 25th, 2024.

Version 0.2 (accepted)

· Jun 25, 2024 · Academic Editor

Accept

The authors completed the revision of the manuscript based on suggestions provided by the reviewers. I confirm that all requests and comments from reviewers have been adequately addressed with valid additions and justifications.

Version 0.1 (original submission)

· Apr 30, 2024 · Academic Editor

Major Revisions

The study is interesting, but needs some modifications to increase the validity of the results.

I would recommend a more in-depth and detailed description of the experimental setup and results.

Furthermore, it would be interesting to more carefully describe the contribution and novelty of the study compared to the existing literature.

·

Basic reporting

The paper discusses the importance of selecting the appropriate risk assessment method (RAM) for a given work environment. With numerous RAMs available, choosing the right one is crucial. The study proposes a hybrid approach using k-means clustering and support vector machine (SVM) classification algorithms to determine the most suitable RAMs for different sectors. The approach involves dividing the dataset into subsets using k-means, running SVM on each subset, and combining the results. This creates a flexible structure with separate threshold values for each sub-cluster, providing machine support for selecting the most suitable RAMs. The proposed hybrid method outperforms other machine learning algorithms. I

Experimental design

The paper discusses the importance of selecting the appropriate risk assessment method (RAM) for a given work environment. With numerous RAMs available, choosing the right one is crucial. The study proposes a hybrid approach using k-means clustering and support vector machine (SVM) classification algorithms to determine the most suitable RAMs for different sectors. The approach involves dividing the dataset into subsets using k-means, running SVM on each subset, and combining the results. This creates a flexible structure with separate threshold values for each sub-cluster, providing machine support for selecting the most suitable RAMs. The proposed hybrid method outperforms other machine learning algorithms. I It Addresses a significant problem in risk assessment It Proposes a novel hybrid approach combining k-means and SVM and Demonstrates improved results compared to other machine learning algorithms
Weaknesses:
Limited explanation of the k-means and SVM algorithms
Unclear how the 26 sectors, 10 RAMs, and 10 criteria were selected
Lack of detailed results and performance metrics
Suggestions for Improvement:
Provide a more comprehensive explanation of the machine learning algorithms used
Clarify the selection process for sectors, RAMs, and criteria
Include more detailed results, performance metrics, and comparisons with other methods

Validity of the findings

The paper discusses the importance of selecting the appropriate risk assessment method (RAM) for a given work environment. With numerous RAMs available, choosing the right one is crucial. The study proposes a hybrid approach using k-means clustering and support vector machine (SVM) classification algorithms to determine the most suitable RAMs for different sectors. The approach involves dividing the dataset into subsets using k-means, running SVM on each subset, and combining the results. This creates a flexible structure with separate threshold values for each sub-cluster, providing machine support for selecting the most suitable RAMs. The proposed hybrid method outperforms other machine learning algorithms. I It Addresses a significant problem in risk assessment It Proposes a novel hybrid approach combining k-means and SVM and Demonstrates improved results compared to other machine learning algorithms There is limited explanation of the k-means and SVM algorithms
It is little unclear how the 26 sectors, 10 RAMs, and 10 criteria were selected.

Additional comments

The paper could have provided a more comprehensive explanation of the machine learning algorithms used and it would be great to Clarify the selection process for sectors, RAMs, and criteria
Include more detailed results, performance metrics, and comparisons with other methods

·

Basic reporting

1. Numerical results and values should be included in the abstract part.
2. Novel experimental work is missing
3. Results are not defined accurately.

Experimental design

poor experiment work

Validity of the findings

no novel work is find

Additional comments

Major revisions are required.

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.