Differential Evolution with Adaptive Grid-Based Mutation Strategy for Multi-Objective Optimization
Round 1
Reviewer 1 Report
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer,
"Please see the attachment."
Regards
Samira
Author Response File: 
Author Response.docx
Reviewer 2 Report
A multi-objective optimization algorithm based on adaptive grid differential evolution is proposed in the manuscript. The theme of the manuscript is interesting, but the manuscript needs to be further supplemented and improved.
(1) In lines 40 and 41 of the manuscript, "However, few works have been conducted on designing efficient selection operators to maintain population diversity." is mentioned and references [16-18] are cited. Are these three references positive examples of designing effective selection operators to maintain population diversity?
(2) If references [16-18] are positive cases, they should be discussed as comparison algorithms. The existing comparison methods in the manuscript lack novel algorithms.
(3) The performance metrics used in the manuscript are "hypervolume indicator", and I would prefer to see other performance metrics used together to fully illustrate the advantages of the proposed algorithm, such as "Generational Distance" and "Inverted Generational Distance"
(4) Table 6 in the manuscript and the calculation in reference [58] also use hypervolume as the performance metric, but there is a large difference in the values in the same case, please explain the reason.
(5) References are too old to reflect the advantages of manuscripts over novel research.
(6) A mutation strategy, DE/current-to-best/1, was mentioned in line 11 and again in section 3.2. However, the theory of the mutation strategy and its abbreviated meaning are not clearly explained, nor are the references accurately labeled.
(7) I think the keyword "Crossover" has too many meanings to accurately express the content in the manuscript.
Author Response
Dear Reviewer,
"Please see the attachment."
Regards
Samira
Author Response File: Author Response.docx
Reviewer 3 Report
Dear authors,
Please consider the following remarks and suggestions in order to improve your work by providing convincing justifications and comprehensive explanations to amend ambiguities.
- Please add a flowchart, which clearly reflect the methodology of the proposed scheme.
- The scenario description needs further improvements.
- The contribution of the work has to be better highlighted to show the novelty and significance of the work against the previously conducted studies in the literature and to better demonstrate the knowledge gap in this topic.
- The quality of some figures must be improved. (e.g. Fig. 1)
- The results of performance comparison of ad-GrMODE with algorithms for the DTLZ and WFG problems are not well matured.
- How the perturbation and crossover parameters are optimally tuned?
Author Response
Dear Reviewer,
"Please see the attachment."
Regards
Samira
Author Response File: Author Response.docx
Reviewer 4 Report
My comments can be found in the attached file
Comments for author File: Comments.pdf
Author Response
Dear Reviewer,
"Please see the attachment."
Regards
Samira
Author Response File: Author Response.docx
Reviewer 5 Report
Dear authors, I read the article Differential Evolution with Adaptive Grid-based Mutation 2 Strategy for Multi-objective Optimization, it is an interesting article and here are some observations that could improve your article:
1.- Quantitative results must be mentioned in the abstract.
2.- Despite citing articles [3] and [4], the authors must consider that according to the No Free Lunch theorem, no search and optimization algorithm is better than another for all applications. Additionally, the references are from 2006 and 2013, leaving out some new generation algorithms. If it is better in the specific problem chosen, it should be noted with more recent bibliography.
3.- It should be compared with some new generation method without specific parameters.
4. The authors should consider the existing hyperparameter selection methods and the differences effect with the proposed method.
5.- do you considered the convergence graphs?
6.- The quality of the graphics should be improved.
7.- The results should be discussed extensively.
Author Response
Dear Reviewer,
"Please see the attachment."
Regards
Samira
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors have done a good job of revising and supplementing the manuscript in accordance with the comments, and I think the manuscript is acceptable in its present form.
Reviewer 4 Report
Thanks for considering my comments. In my original review, I predicted that readership of the manuscript would be limited to a small audience who were capable of understanding understanding the highly technical style of presentation. I suggested that the authors could provide a brief synopsis that would describe their work in a way that would offer a broader perspective for readers who are not mathematicians. I can't see that any of the modifications made any progress toward this goal. I maintain my original view: the manuscript is evidence of a high level of achievement, and I do not question the quality of the work, but it will be understandable only to a small audience. I suggest that acceptance or rejection can best be made by journal editors based on readership considerations.
Reviewer 5 Report
The authors have addressed my concerns.
