An Innovative Enhanced JAYA Algorithm for the Optimization of Continuous and Discrete Problems

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Queuing Search Algorithm (QSA) (J. Zhang et al., 2018). -> Queuing Search Algorithm (QSA) (Zhang et al., 2018).

State-of-art metaheuristics such as CMAES (http://cma.gforge.inria.fr/) and coyote algorithm (https://github.com/jkpir/COA) could be considered in the comparative study.

 

A full statistical analysis of the optimizers comparison must be presented based on performance metrics and significance nonparametric tests.

Authors could perform statistical tests (e.g. Friedman test + posthoc Nemenyi test) to compare algorithms and discuss the results in the paper.

 

See examples in the following papers:

Recent trends in the use of statistical tests for comparing swarm and evolutionary computing algorithms: Practical guidelines and a critical review Swarm and Evolutionary Computation Volume 54 May 2020 Article 100665 J. Carrasco, S. García, M. M. Rueda, S. Das, F. Herrera https://www.sciencedirect.com/science/article/pii/S2210650219302639

Analyzing convergence performance of evolutionary algorithms: A statistical approach Information Sciences Volume 28924 December 2014 Pages 41-58 Joaquín Derrac, Salvador García, Sheldon Hui, Ponnuthurai Nagaratnam Suganthan, Francisco Herrera https://www.sciencedirect.com/science/article/pii/S0020025514006276

To enhance the language of the introduction and related works, one could consult recent references from IEEE, Springer, and Elsevier regarding Jaya. An examples is: A comprehensive review on Jaya optimization algorithm, https://link.springer.com/article/10.1007/s10462-022-10234-0

 

 

 

Comments on the Quality of English Language

English needs improvements.

Author Response

Dear Editors and Reviewers,

We would like to express our deepest gratitude to you and dear reviewers for the constructive and valuable comments. It is notable that all comments of dear reviewers have been addressed in the best manner as follows. The revised parts within the article have been highlighted in green color.

Manuscript ID: algorithms-3157409

Type: Article

Title: An Ingenious Enhanced JAYA Algorithm for Optimization of Continuous and Discrete Problems

Authors: Jalal Jabbar Bairooz *, Farhad Mardukhi

 

Reviewer 1:

 

Comments and Suggestions for Authors:

Thank you for your valuable comments and suggestions, which have greatly contributed to improving the quality and clarity of this work. Your comments were applied into manuscript.

 

Queuing Search Algorithm (QSA) (J. Zhang et al., 2018). -> Queuing Search Algorithm (QSA) (Zhang et al., 2018).

State-of-art metaheuristics such as CMAES (http://cma.gforge.inria.fr/) and coyote algorithm (https://github.com/jkpir/COA) could be considered in the comparative study.

A full statistical analysis of the optimizers comparison must be presented based on performance metrics and significance nonparametric tests.

Authors could perform statistical tests (e.g. Friedman test + posthoc Nemenyi test) to compare algorithms and discuss the results in the paper.

See examples in the following papers:

Recent trends in the use of statistical tests for comparing swarm and evolutionary computing algorithms: Practical guidelines and a critical review Swarm and Evolutionary Computation Volume 54 May 2020 Article 100665 J. Carrasco, S. García, M. M. Rueda, S. Das, F. Herrera https://www.sciencedirect.com/science/article/pii/S2210650219302639

Analyzing convergence performance of evolutionary algorithms: A statistical approach Information Sciences Volume 28924 December 2014 Pages 41-58 Joaquín Derrac, Salvador García, Sheldon Hui, Ponnuthurai Nagaratnam Suganthan, Francisco Herrera https://www.sciencedirect.com/science/article/pii/S0020025514006276

To enhance the language of the introduction and related works, one could consult recent references from IEEE, Springer, and Elsevier regarding Jaya. An example is: A comprehensive review on Jaya optimization algorithm, https://link.springer.com/article/10.1007/s10462-022-10234-0

 

Response:  A Friedman test has been added to the manuscript based on the introduced references. These references were also cited for future readers to know such tests. For review, please see page 26.

 

Comments on the Quality of English Language:

English needs improvements.

Response:  Much appreciated for pointing this item out. The language of the manuscript has been significantly improved based on your comments.

Reviewer 2 Report

Comments and Suggestions for Authors

This article proposes an enhanced JAYA (EJAYA) method for removing its inherited shortcomings, resulting in improved convergence and search capabilities when confronted with different problems.

The problem being solved in the manuscript is relevant. There are a number of suggestions and comments.

 

1. The arrangement of References in the journal Algorithms should be in the order of mention in the text and in square brackets with the number.

2. Algorithms 1 and 2 do not need to be labeled as tables.

3. In Subsection 3.2.3, describe the variable 𝑟_j.

4. Line 230: Explain this moment "If it reaches the MI, it is not stopped". Why the algorithm will not "loop" in this case?

5. The authors run the algorithms 30 times and calculate the average value. Why not the median, for example.

6. The main criteria for the “success” of the algorithm are:

1) the time it took the algorithm to solve the problem (the faster, the better);

2) the amount of memory required for the algorithm to work (the less, the better).

Can you indicate how the computation time was reduced after applying the proposed algorithm? Have the computation power requirements increased? Judging by the graphs of the results of running the proposed algorithm, 1000 iterations are not always enough for its convergence. How is this reflected in the convergence time compared to other algorithms.

7. The authors did not indicate the parameters of the computer system used for the experiments.

8. The heuristic method assumes a solution with an acceptable margin of error. How do the authors define these limits?

9. I would like to see the practical results of the proposed algorithm on large size datasets.

10. In Algorithm 2, correct the numbering of steps.

11. In section 4, it is better to make subsections 4.1 and 4.2.

12. Read the text carefully, there are minor errors, for example:

- line 213: probably subsection 3.1 instead of section 2.1;

- after a reference in the text to Fig. 2, the next one immediately follows to Fig. 4;

- typo in the title of Figure 3 "F612".

Also, look carefully at the layout of the manuscript (e.g., numbering of formulas is done in parentheses and aligned on the right edge).

Author Response

Dear Editors and Reviewers,

We would like to express our deepest gratitude to you and dear reviewers for the constructive and valuable comments. It is notable that all comments of dear reviewers have been addressed in the best manner as follows. The revised parts within the article have been highlighted in green color.

Manuscript ID: algorithms-3157409

Type: Article

Title: An Ingenious Enhanced JAYA Algorithm for Optimization of Continuous and Discrete Problems

Authors: Jalal Jabbar Bairooz *, Farhad Mardukhi

Reviewer 2:

 

Comments and Suggestions for Authors

This article proposes an enhanced JAYA (EJAYA) method for removing its inherited shortcomings, resulting in improved convergence and search capabilities when confronted with different problems.

The problem being solved in the manuscript is relevant. There are a number of suggestions and comments.

Thank you for your valuable comments and suggestions, which have greatly contributed to improving the quality and clarity of this work. Your comments were applied into manuscript.

1. The arrangement of References in the journal Algorithms should be in the order of mention in the text and in square brackets with the number.

Response:  Thanks. It has been done.

2. Algorithms 1 and 2 do not need to be labeled as tables.

Response:  Great comment. They were removed.

3. In Subsection 3.2.3, describe the variable ?_j.

Response:  It has been described based on your great suggestion.

4. Line 230: Explain this moment "If it reaches the MI, it is not stopped". Why the algorithm will not "loop" in this case?

Response:  Thanks for your great comment. It was a typo issue. It has been corrected as can be seen on Page 6.

5. The authors run the algorithms 30 times and calculate the average value. Why not the median, for example.

Response:  Thank you for your suggestion regarding the use of the median instead of the average. We chose to use the average because it provides a measure that takes all the results from the 30 runs into account, giving us a comprehensive view of the algorithm's overall performance. The average is particularly useful in our study to evaluate the general tendency and compare different algorithms under consistent conditions. This explanation was also added to the manuscript based on your suggestion for future readers on Pages 7-8.

6. The main criteria for the “success” of the algorithm are:

1) the time it took the algorithm to solve the problem (the faster, the better);

2) the amount of memory required for the algorithm to work (the less, the better).

Can you indicate how the computation time was reduced after applying the proposed algorithm? Have the computation power requirements increased? Judging by the graphs of the results of running the proposed algorithm, 1000 iterations are not always enough for its convergence. How is this reflected in the convergence time compared to other algorithms.

Response:  according to your great suggestion, the algorithms were run to calculate the computational burden and the results were provided on Page 26.  As can be seen, the proposed algorithm consumes less than 1 second. Therefore, the proposed method not only enhanced the performance of the algorithm, but it also reduced the time complexity.

7. The authors did not indicate the parameters of the computer system used for the experiments.

Response:  Thanks. It has been mentioned based on your great comment on Page 8.

8. The heuristic method assumes a solution with an acceptable margin of error. How do the authors define these limits?

Response:  Great comment. This has been explained in the manuscript on Page 7 for future readers. For your information, we tried to keep the solutions between acceptable limits, by a comparison between generated solution and the boundaries.

9. I would like to see the practical results of the proposed algorithm on large size datasets.

Response:  Thanks for your suggestion. Because I am on the edge of the graduation deadline, I do not have sufficient time to apply it to practical results. It means I have to provide the paper for acceptance to the University so that I would be eligible to defend my course. However, we will do that in the future as a new paper. Your fantastic suggestion has also been added to the conclusion as future work.

10. In Algorithm 2, correct the numbering of steps.

Response:  Great comment. It has been corrected.

11. In section 4, it is better to make subsections 4.1 and 4.2.

Response:  Great comment. This has been done.

12. Read the text carefully, there are minor errors, for example:

- line 213: probably subsection 3.1 instead of section 2.1;

Response:  You are right. It has been updated to the 3.1.

- after a reference in the text to Fig. 2, the next one immediately follows to Fig. 4;

Response:  Thanks a lot. The figure numbers and their reference in the text were reviewed and corrected.

- typo in the title of Figure 3 "F612".

Response:  Thanks a lot. It has been corrected.

Also, look carefully at the layout of the manuscript (e.g., the numbering of formulas is done in parentheses and aligned on the right edge).

Response:  Thanks. The manuscript was revised and the layout such as formulas, etc., was improved.

 

Reviewer 3 Report

Comments and Suggestions for Authors

Authors are suggested consider incorporating following changes in the manuscript to further improve its quality:

1. In the statement: "it faces challenges in adequately exploring the search space and occasionally becoming trapped in local minima. In other words, because it employs a single learning technique with low population diversity, JAYA is vulnerable to being caught in local optima when confronted with complicated optimization problems."

 

It would be more convincing if the authors justify this statement with some example.

 

2. Authors are suggested to include some more recent papers in the literature review section. some of the papers are suggested below:

http://dx.doi.org/10.5267/j.ijiec.2019.6.002

https://doi.org/10.1016/j.knosys.2024.111578

https://doi.org/10.1007/s00500-023-09276-5

 

The first paper is also the parameter-less algorithm proposed by same author Rao and the second paper is a work based on it. 

 

3. In section 3.1 Authors said that JAYA algorithm is employing single learning technique. It is not clear to readers that what is that single learning technique? and why is it not good? what is the shortcoming of this technique (if any)

 

4. In section 3.2.3,what is 'a'? what  is the effect of a on the algorithm's exploration and exploitation capability? please explain.

 

5. How did the authors arrived at values AW=0.3 and a=3

 

6. Authors are suggested to compare the results of their proposed algorithm with Rao-1, Rao-2 and Rao-3 algorithms from http://dx.doi.org/10.5267/j.ijiec.2019.6.002.

 

7. In section 4.1.2 authors should explain what modifications are required in the EJAYA algorithms to accommodate the needs of a discrete optimization problem like  feature selection. How did they converted from continuous space to discrete space (through transfer functions or any other method)?

 

Comments on the Quality of English Language

Kindly proofread once to correct the typos and some grammatical errors.

Author Response

Dear Editors and Reviewers,

We would like to express our deepest gratitude to you and dear reviewers for the constructive and valuable comments. It is notable that all comments of dear reviewers have been addressed in the best manner as follows. The revised parts within the article have been highlighted in green color.

Manuscript ID: algorithms-3157409

Type: Article

Title: An Ingenious Enhanced JAYA Algorithm for Optimization of Continuous and Discrete Problems

Authors: Jalal Jabbar Bairooz *, Farhad Mardukhi

Reviewer 3:

 

Comments and Suggestions for Authors

 

Authors are suggested to consider incorporating the following changes in the manuscript to further improve its quality:

Thank you for your valuable comments and suggestions, which have greatly contributed to improving the quality and clarity of this work. Your comments were applied into manuscript.

 

1. In the statement: "it faces challenges in adequately exploring the search space and occasionally becoming trapped in local minima. In other words, because it employs a single learning technique with low population diversity, JAYA is vulnerable to being caught in local optima when confronted with complicated optimization problems." It would be more convincing if the authors justify this statement with some example.

 

Response:  thanks. That part has been updated based on your great comment.

 

 

2. Authors are suggested to include some more recent papers in the literature review section. some of the papers are suggested below:

http://dx.doi.org/10.5267/j.ijiec.2019.6.002

https://doi.org/10.1016/j.knosys.2024.111578

https://doi.org/10.1007/s00500-023-09276-5

The first paper is also the parameter-less algorithm proposed by same author Rao and the second paper is a work based on it. 

Response:  Thanks, these references were cited in the paper based on your comment.

 

3. In section 3.1 Authors said that JAYA algorithm is employing single learning technique. It is not clear to readers that what is that single learning technique? and why is it not good? what is the shortcoming of this technique (if any)

Response:  based on your comment, that part has been expanded for future readers.

 

4. In section 3.2.3,what is 'a'? what  is the effect of a on the algorithm's exploration and exploitation capability? please explain.

 Response:   it has been introduced based on your comment.

 

5. How did the authors arrived at values AW=0.3 and a=3

Response:   we run the algotithm for different values of mentioned parameters and then compare objective function. From comparisons, algorithm found better solution (minimum objective function) under these parameters. This has been added to the paper for future readers based on your comment.

 

6. Authors are suggested to compare the results of their proposed algorithm with Rao-1, Rao-2 and Rao-3 algorithms from http://dx.doi.org/10.5267/j.ijiec.2019.6.002.

Response:  Thanks for your suggestion. Because I am on the edge of the graduation deadline, I do not have sufficient time to apply it. It means I have to provide the paper for acceptance to the University so that I would be eligible to defend my course. However, we will do that in the future as a new paper.

 

 

7. In section 4.1.2 authors should explain what modifications are required in the EJAYA algorithms to accommodate the needs of a discrete optimization problem like  feature selection. How did they converted from continuous space to discrete space (through transfer functions or any other method)?

Response:  According to your suggestion, it has been added to the manuscript for a discrete version of the proposed algorithm.

 

Reviewer 4 Report

Comments and Suggestions for Authors

The authors have proposed enhanced Jaya algorithm, however, many variants are already available in many literature. What is the special mechanism used in this algorithm? The authors have takes FS as real world problem however, FS problem is binary problem but the authors haven't discussed about the binary algorithm transformation. Why other real-world problems are not considered for the validation? What is the complexity of the proposed algorithm? The lterature review must be improved by referring to newly published JAYA variants. What is the future scope of the algorithm? Many grammatical mistakes and typos are there. Correct it and possibly go for English proofreading. 

Comments on the Quality of English Language

Corrections are required.

Author Response

Dear Editors and Reviewers,

We would like to express our deepest gratitude to you and dear reviewers for the constructive and valuable comments. It is notable that all comments of dear reviewers have been addressed in the best manner as follows. The revised parts within the article have been highlighted in green color.

Manuscript ID: algorithms-3157409

Type: Article

Title: An Ingenious Enhanced JAYA Algorithm for Optimization of Continuous and Discrete Problems

Authors: Jalal Jabbar Bairooz *, Farhad Mardukhi

Reviewer 4:

 

Comments and Suggestions for Authors

 

The authors have proposed enhanced Jaya algorithm, however, many variants are already

available in many literature. What is the special mechanism used in this algorithm? The

authors have takes FS as real world problem however, FS problem is binary problem but the

authors haven't discussed about the binary algorithm transformation. Why other real-world

problems are not considered for the validation? What is the complexity of the proposed

algorithm? The lterature review must be improved by referring to newly published JAYA

variants. What is the future scope of the algorithm? Many grammatical mistakes and typos are

there. Correct it and possibly go for English proofreading. 

Response:

Thank you for your valuable comments and suggestions, which have greatly contributed to improving the quality and clarity of this work. Your comments were applied to the manuscript.

The new references [57]to [63] were added to the paper as can be seen on page 3.

Besides, the binary version of the algorithm is also presented in Algorithm 3 on page 7.

The future scops were also added to the conclusion for future readers.

The English of the paper was also enhanced significantly.

 

 

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The current versin of the paper is improved.

Note: Verify if all variables are defined in the article.

Comments on the Quality of English Language

English needs some improvements.

Reviewer 2 Report

Comments and Suggestions for Authors

The manuscript is markedly improved. The authors have amended and clarified in line with my comments.

In subsection 3.2.3, when describing the variable 𝑟_j, the underscore indicates the lower case (index) “j”.

I have a hieroglyph drawn in the corrected version of the manuscript in formulas 1, 3, 5. Check.

Reviewer 3 Report

Comments and Suggestions for Authors

Accept.