Application of Multi-Objective Hyper-Heuristics to Solve the Multi-Objective Software Module Clustering Problem
Round 1
Reviewer 1 Report
The paper entitled "An Application of Multi-objective Hyper-heuristic to Solving the Multi-objective Software Module Clustering Problem" proposes a multi-objective hyper-heuristic (MOHH) method to solve the multi-objective module clustering optimization problem. It aims to lower the coupling, increase the cohesion, and ensure high modularization quality. The proposed method is tested on two datasets named mutins and telnet2 by using several external validation metrics such as RNI, SSC, and UD.
In general, the topic invested in the paper is interesting and meets the scope of the AS journal. However, I have several concerns about the structure and formulation of the paper. The authors need to revise the paper to further improve its quality.
First, regarding the structure, the authors should reorganize the structure of the paper so that readers can easily follow the content. In the Introduction, subsections 1.1 and 1.2 should be moved to the section called "Preliminaries and Related work" in which authors should introduce the latest works in this field. I can find out many works focused on the same topics as this paper. In addition, the authors should discuss the importance of data mining and data-driven approaches for SMC in the Introduction section.
All figures are not in a good shape. Authors should revise all figures to make the text clearer, copiable, and not broken when zooming out.
The pseudo-code in Table 1 should be revised in a form of an algorithm, the authors can follow the conventional way to make an Algorithm from [https://en.wikibooks.org/wiki/LaTeX/Algorithms#/media/File:Latex-algorithm2e-if-else.png]
Table 2 and sections 2.1 should be placed after the first paragraph of section "Materials and Methods". Then, introduce the proposed framework and pseudo-code.
Also in the section "Materials and Methods", authors should use a small dataset to make examples to illustrate all definitions and formulations in the paper.
In section 4, use boldface numbers to highlight the best results in Tables 8 and 9. Also, the authors should discuss how significant the obtained RNI, UD and SSC results are?
In section 4, although the finding in this paper is supported by the results, the authors should discuss possible methods for this problem. I still think there are several ways to improve the interpretability of the clustering performance. A possible solution is to use hierarchical clustering. Here are several good examples that authors should refer into the discussion [https://doi.org/10.3390/app12010072], [https://doi.org/10.1007/978-981-15-1209-4_1], [https://doi.org/10.3390/app112311122].
Carefully revise the paper to fix all typos and grammar mistakes.
Author Response
Please see the attachment
Author Response File: 
Author Response.docx
Reviewer 2 Report
The authors focused on the multi-objective optimization. In general, this paper is poor writing. Firstly, there is some gramma problems with the title. “To solving” should be “to solve”. The overall organize is bad. It is suggested they authors should re-check the full text. In addition, the contribution is trivial. I cannot find the main contribution or challenge they have made. The quality of Figures is too low and also there is no adequate explain for them. Besides, the explanation for the Table is missing. The pseudocode is in bad format.
Author Response
"Please see the attachment."
Author Response File: Author Response.docx
Reviewer 3 Report
- How the multi-objective hyper-heuristic (MOHH) balance exploration and exploitation to solve Software module clustering problem ?
- You should present the results for Mutins and Telnet2 systems after applying NSGA-II, SPEA and MOGA ?
Author Response
"Please see the attachment."
Author Response File: Author Response.docx
Reviewer 4 Report
This paper applies the multi-objective choice function-great deluge hyper-heuristic (HHMO_CF_GDA) approach to the multi-objective software module clustering problem. However, the authors do not make it clearly why the HHMO_CF_GDA approach is selected here. Moreover, the HHMO_CF_GDA approach was proposed in other existing work, and the superiority of this approach to other methods is not presented in this paper. The objective functions of the software module problem should be described more clearly.
Author Response
"Please see the attachment."
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
I have checked this revision. The authors have significantly improved the quality of the paper. Thus, I vote for an acceptance.
Author Response
Reviewer 1
I have checked this revision. The authors have significantly improved the quality of the paper. Thus, I vote for an acceptance.
Author response: We thank the reviewer for his/ her review and the comments. Although the reviewer found the quality of the paper is improved and the paper is in the accepted form, we updated the manuscript based on the other reviewers' suggestions by (a) adding more experiments and results, (b) revising the entire manuscript, and adding more information and details, and (c) the entire manuscript has extensively edited for the second time and proofread by experts in English editing in SCRIBENDI INC.( The English editing certificate is attached)
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Although the authors have made some revions, there still a lot of issues needs to be addressed. It is suggested the authors should carefully rewrite the whole paper.
Author Response
Reviewer 2
Although the authors have made some revions, there still a lot of issues needs to be addressed. It is suggested the authors should carefully rewrite the whole paper.
Author response: This concern has been adopted
Author action: we updated the manuscript based on the other reviewers' suggestions by (a) adding more experiments and results, (b) revising the entire manuscript and adding more information and details, and (c) the entire manuscript has extensively edited for the second time and proofread by experts in English editing in SCRIBENDI INC.( The English editing certificate is attached)
Author Response File: Author Response.pdf
Reviewer 3 Report
Add more results.
Add more observations and future research directions
Author Response
Reviewer 3
Add more results.
Author response: This concern has been adopted
Author action: We updated the Section 4 Experiments and Section 5 Results based on the reviewer's suggestion and added more experiments and results. We conducted a comparison between the HHMO_CF_GDA approach and individual low-level MOEA algorithms to evaluate the performance of HHMO_CF_GDA.
Add more observations and future research directions
Author response: This concern has been adopted
Author action: We updated the manuscript by adding more observations at the end of the results and discussion section in line 339. We also added more future research directions at the end of the conclusion section.
Reviewer 4 Report
The authors have revised this paper according my suggestion. However, I still think they have not describe the problem and the method clearly enough. in the Section 3.1.
Author Response
Reviewer 4
The authors have revised this paper according my suggestion. However, I still think they have not describe the problem and the method clearly enough. in the Section 3.1.
Author response: This concern has been adopted
Author action: We updated the manuscript by adding more details of the problem description, and we add more explanation of the method in Section 3.
