Multi-Strategy-Improved Growth Optimizer and Its Applications
Round 1
Reviewer 1 Report
Comments and Suggestions for Authors1. Abstract needs to be further enhanced. The descriptions related to proposed methodology are too limited. Meanwhile, the descriptions related to the experimental studies are quite lengthy.
2. Information provided in Lines 58 to 84 are too lengthy and can be shorten for better clarity.
3. The problem statements and research motivations that lead to current research are not clearly explained. Authors are required to provide more in-depth discussion on the current issue encountered in research related to GO. Currently, there are no coherence observed between the problem statements and the proposed modifications applied on the new GO variant.
4. Lines 104-110: Descriptions related to the exploration and exploitation strategies are quick generic, where the authors did not highlight any specific technical details. Further elaboration from authors are needed.
5. Similar issues are observed from the contributions of current works described in Lines 114 to 121. Authors should focus more on the descriptions related to the proposed modification made on the GO variant instead of the types of minimization problems used for performance evaluation. Please rewrite the technical contributions.
6. Authors are required to provide the literature review related to the recent works of GO since it has been introduced in 2022.
7. It is necessary for the authors to cite the relevant works to justify the importance of having a modified initialization scheme to improve the solution quality. For instance:
https://www.sciencedirect.com/science/article/pii/S1110016822003489
Authors may consider to cite other relevant works that might be applicable.
8. Please justify the parameter selection of a and b as outlined in Line 246.
9. Further clarification is needed to justify the formulation of Eq. (14). For instance, how to justify the selection of pi and 8 wthin the equations? The theoretical explanation is missing.
10. One of the major issues with this manuscript is the lacking of detailed explanation about the proposed mechanisms. For instance, it is not clear how Eq. (16) can be useful to promote exploration process. Similar issues are observed from Eq. (18) and (19), where authors claims to be useful in promoting the exploitation. A more detailed exploitation is needed for authors to justify how the proposed modifications can lead to the balancing of exploration and exploitation searches.
11. Please analyse the computational complexity of the proposed algorithm using Big O notation and compared with the original GO.
12. How does the authors measure the population diversity in Section 4.3.1? Please present the equation used.
13. Similarly, it is not clear how the authors measure the exploration and exploitation of algorithm in Section 4.3.2
14. Line 573: The parameter settings of K=5 for KNN algorithm has nothing to do with the K-fold cross validation. Please rectify this misconception.
15. The graphical illustration in Figure 10 is quite confusing. Authors are advised to change the way of presenting the data more effectively.
16. What are the constraints handling techniques used by the proposed method to solve the engineering problems mentioned in Section 4.5?
Comments on the Quality of English LanguageSome typo and grammatical issues can be observed from the manuscripts. Authors are required to proofread the manuscript before resubmission (if applicable).
Author Response
Dear reviewers
Thank you very much for your time during the review process. On behalf of all the contributing authors, I would like to express my sincere thanks to you for your constructive comments on our article titled “Multi-strategy Improved Growth Optimizer and its Applications” (Manuscript No. axioms-2925417). All these comments are valuable and helpful for us to improve the article. Based on your comments, we have revised the manuscript extensively to make our results more convincing. The following document is a point-by-point response to the reviewers.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe idea is interesting and the article is well written. I have the following minor comments to further improve the quality of the manuscript.
This paper proposes an enhanced Growth Optimizer (GO) called CODGBGO to address the limitation of GO, such as, local stagnation when it comes to discretization, high dimensionality, and multi-constraint problems.
The performance of CODGBGO in addressing high-dimensional numerical optimization problems is initially validated through the utilization of the CEC2017 and CEC2020 test sets. Subsequently, feature selection problems are employed to evaluate the effectiveness of CODGBGO in discretized problem scenarios. Lastly,4 real-world engineering multi-constraint optimization problems are employed to assess the performance of CODGBGO for high-dimensional and multi-constraint problem domains. However, it is suggested to assess the true potential of proposed scheme for solving challenging nonlinear problems such as, Design of nonlinear marine predator heuristics for Hammerstein autoregressive exogenous system identification with key-term separation
The authors compared the proposed algorithm with different other methods. But authors have not compared the proposed CODBGO to chaotic and fractional based optimizer. While chaotic and fractional modified optimizers are proposed to effectively address the similar challenges addressed by the authors. In this regard, authors are suggested to see the following literature and provide the comparison with the recent chaotic and fractional optimizers, Variants of chaotic grey wolf heuristic for robust identification of control autoregressive model, Knacks of fractional order swarming intelligence for parameter estimation of harmonics in electrical systems. If comparison is not possible, at least include these in the introduction section to give fair and better insight to the readers regarding recent metaheuristics.
Author Response
Dear reviewers
Thank you very much for your time during the review process. On behalf of all the contributing authors, I would like to express my sincere thanks to you for your constructive comments on our article titled “Multi-strategy Improved Growth Optimizer and its Applications” (Manuscript No. axioms-2925417). All these comments are valuable and helpful for us to improve the article. Based on your comments, we have revised the manuscript extensively to make our results more convincing. The following document is a point-by-point response to the reviewers.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsPlease, check the text for typos/technical errors. For example:
1. "The Growth Optimizer (GO) is a novel optimization algorithm proposed in 2022 that has garnered significant attention due to its simple structure and impressive solution performance," - point in the end of sentence; citation needed
2. "Inspired by the process of personal growth, GO is introduced in 2022 as a novel optimizer." - citation needed
3. "Section V provides the conclusion and Conclusions and future directions for work." or "All experiments were conducted on an AMD Ryzen 5 3600 6-core processor 3.60 GHz All experiments were conducted on AMD Ryzen 5 3600 6-core processor at 3.60 GHz, with Windows 11 as the operating system, and all codes were run in MATLAB R2021b environment."
4. "where the mathematical expression for the circle chaos 243 mapping is Eq. (9)." - citation needed
5. avoid multiple introduction of the notations and facts:
- "Step 1: Initialize the run parameters containing the population size (N), the 204 dimension of the problem to be solved (D), the upper bound (ub) and lower bound (lb)" - page 5
- "where ub and lb represent the upper and lower bounds of the problem, respectively, D indicates the number of problem variables, N represents population size,"- page 7
- "Step 1: Initialize the run parameters containing the population size (N), the dimension of the problem to be solved (D), the upper bound (ub) and lower bound (lb)" - page 9
6. The notation (chaos value) on the Y-axis in Fig. 1a is wrong
7. The last results in Table 17 are not visible.
8. "In CODGBGO, firstly Provides a good initial population using ...", etc.
Main comments:
1. Why were these particular values chosen? Authors should justify their choice.
"Parameter α is denoted as {0.7, 0.8, 0.9} and parameter β is denoted as {0.85, 0.9, 406 0.95}"
2. Please comment/interpret the result
2.1. "It can be seen from Table 5 that compared to other parameter combinations, parameter combinations {0.8, 0.95} show more competitive results. Therefore, {0.8, 0.95} are selected as the optimal parameter combination for subsequent experiments."
2.2. IEEE CEC2020 test function
- Where are the results of CODGBGO and other 3 algorithms for CEC2020 test functions? Only p-values and Friedman mean rank test results are presented.
2.3. Obviously, a huge amount of numerical experiments have been performed. But, it seems that there is no real discussion of the results. The proposed discussion is a simple description/restatement of the results seen in the tables. There is a lack of analysis - interpretation - why such results are obtained. Because of what specifics of the proposed modified algorithm, it predominantly shows better performance? In cases where another algorithm is better - what could be the reason?
2.4. It would be better if, in the Conclusion section, the authors discuss the main advantages and disadvantages of the proposed approach and then provide the further directions for work.
Author Response
Dear reviewers
Thank you very much for your time during the review process. On behalf of all the contributing authors, I would like to express my sincere thanks to you for your constructive comments on our article titled “Multi-strategy Improved Growth Optimizer and its Applications” (Manuscript No. axioms-2925417). All these comments are valuable and helpful for us to improve the article. Based on your comments, we have revised the manuscript extensively to make our results more convincing. The following document is a point-by-point response to the reviewers.
Author Response File: Author Response.pdf
Reviewer 4 Report
Comments and Suggestions for Authors The article proposes new exploration and exploitation strategies for the Growth Optimizer algorithm. The goal of using the new strategies was to improve the algorithm's maintenance of population diversity, which improves its exploration ability and helps avoid local optima, and to improve its exploitation ability by improving local search. The article is well constructed. It begins with an overview of the current state of research in the field. Then, the research problem was defined, and its solution was proposed. The authors described in detail the operation of the Growth Optimizer algorithm itself, as well as the strategies proposed to improve its performance. The experimental part is particularly extensive, in which the authors presented the results of research aimed at verifying the effectiveness of the proposed strategies and comparing the effectiveness of the proposed algorithm with the entire set of state-of-the-art metaheuristic algorithms. The experiments used 2 sets of test problems, as well as a set of 18 feature selection problems and 4 real-life engineering problems. The experimental results indicated excellent results obtained by the Growth Optimizer algorithm with the proposed exploration and exploitation strategies. Please address the following problems: 1. Can the proposed algorithm be used for multi-objective optimization problems? What would need to be changed in order for it to be used for this type of problem? 2. Can it be applied to combinatorial optimization problems? 3. Please analyze the weaknesses of the proposed approach. In what cases may the obtained results be worse than alternative modern metaheuristic algorithms?Comments on the Quality of English Language
Please improve the English language in terms of grammar and style.
Author Response
Dear reviewers
Thank you very much for your time during the review process. On behalf of all the contributing authors, I would like to express my sincere thanks to you for your constructive comments on our article titled “Multi-strategy Improved Growth Optimizer and its Applications” (Manuscript No. axioms-2925417). All these comments are valuable and helpful for us to improve the article. Based on your comments, we have revised the manuscript extensively to make our results more convincing. The following document is a point-by-point response to the reviewers.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsAuthors have made substantial efforts to address all comments provided in earlier review. No further comments from me.
Reviewer 3 Report
Comments and Suggestions for AuthorsThe authors have revised the article according to my comments. The paper may be accepted for publication.
Comments on the Quality of English LanguageModerate editing of English language is required.
