Reliability Analysis of Gravity Retaining Wall Using Hybrid ANFIS
Round 1
Reviewer 1 Report
Since it targets practical and specific problems, the research findings should be applicable to practice. However, the research is limited to relative comparison of the four proposed methods. It is of value as a case study for relative comparison of methods, but is unlikely to be of any greater value. Below are the reviewer's comments. From a practical point of view, the following points should be clarified in the paper.
１） It is necessary to clarify the setting conditions of the target problem. In other words, how would the method proposed here be used in practice?
２） In general, gravity wall stability calculations consider the friction between the wall and the wedge. Why did you dare not consider it? Also, if you take it into consideration, will the results change?
３） It should be clear how the datasets used for the analysis were created. Specifically, how to determine the median, maximum and minimum values and the number of data.
４） How do you judge whether the model proposed here can be used practically? If you do not expect great accuracy, all four models will be applicable.
５） The novelty of the model itself and the extent to which it gave superior results to conventional methods should be specified. In addition to the conventional method, please include four models and tabulate the advantages and disadvantages of each.
６） 15 page, Table 4： Please consider why the ratings of ANFIS-PSO and ANFIS-FFA are reversed on training (TR) and test data (TS).
Author Response
Respected Reviewer,
We would like to thank the reviewer for his remarkable suggestions. Suggestions were very useful during revision process and have been incorporated in revised manuscript. We believe the quality of the revised paper has been improved significantly after the revision.
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
This paper should be accepted.
But it must be made some modifications and some references must be added.
Comments for author File: 
Comments.pdf
Author Response
Respected Reviewer,
We would like to thank the reviewer for his remarkable suggestions. Suggestions were very useful during revision process and have been incorporated in revised manuscript. We believe the quality of the revised paper has been improved significantly after the revision.
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
A beautiful manuscript is presented for gravity retaining walls, one of the important subjects of geotechnical engineering. Using machine learning to determine the security factor is more advantageous than deterministic approaches. In addition to this advantage, optimized methods were used in the study. The results obtained in this way are further improved. For these reasons, the manuscript can be accepted as it is. We would like to thank the authors for their contributions to the literature. If the article is evaluated in general;
-The purpose of the study is clearly stated.
-General layout and preparation are good. However, when creating a pdf, the shifts in the formulas should be corrected.
- The study results are well presented with innovative graphics. - Improved operational reliability by using a large number of performance parameters.
- The results obtained show that the models are well established.
The manuscript is acceptable as it is.
Author Response
Respected Reviewer,
We would like to thank the reviewer for his remarkable suggestions. Suggestions were very useful during revision process and have been incorporated in revised manuscript. We believe the quality of the revised paper has been improved significantly after the revision.
Please see the attachment
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
It is judged that corrections have been made appropriately to the extent that the author can.
