Next Article in Journal
Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection
Previous Article in Journal
Experimental Study on Pullout Behavior of Coir Geotextiles Based on Transparent Soil
 
 
Article
Peer-Review Record

Improved Binary Grey Wolf Optimization Approaches for Feature Selection Optimization

Appl. Sci. 2025, 15(2), 489; https://doi.org/10.3390/app15020489
by Jomana Yousef Khaseeb 1, Arabi Keshk 2 and Anas Youssef 2,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Appl. Sci. 2025, 15(2), 489; https://doi.org/10.3390/app15020489
Submission received: 31 October 2024 / Revised: 19 December 2024 / Accepted: 20 December 2024 / Published: 7 January 2025
(This article belongs to the Section Computing and Artificial Intelligence)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper proposes a hybrid algorithm based on gray wolf optimization and binary particle swarm optimization for feature selection. Multiple solution selection methods are adopted for comparison. Experiments are performed on multiple classification tasks to show the better performance of the hybrid algorithm. There are some issues to address:

1.     The motivation of the combination of GWO and PSO should be better explained. How does PSO overcome the local optima?

2.     The description of the methods could be re-organized since most parts in multiple methods are the same and only the solution selection operator is different.

3.     More discussions on the effect of the different solution comparison methods could be added. Why

4.     More details of the dataset could be provided. For example, the sample size of each class in the datasets.

5.     Why is the population size set as 10? The problem dimension seems large. The effect of the population size should be tested.

6.     More state-of-the-art algorithms for feature selection should be compared.

7.     The presentation of the paper could be greatly improved. For example, “for Optimizing Feature Selection” in the title could be revised as “for feature selection”.

Comments on the Quality of English Language

The quality of English language could be improved.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The major contribution of the paper is to enhance the accuracy of the feature selection process while selecting the least possible number of features.

The major strength of this paper is the evaluation of the proposed IBGWO approach. The data and detailed analysis are interesting.

The weaknesses of this paper include:

1)            The grammar must be improved. The abstract can be shortened. The terminology should be consistent throughout the paper.

2)            The organization and clarity need a lot of work. There are too many terms and abbreviations. There should be a table to explain these.

3)            Please consider enhancing the scientific soundness. What are the three proposed approaches?

4)            Please explain the originality of this paper. For example, Table 3 can use quantities instead of check marks.

 

5)            What is the specific research question? There is insufficient cohesiveness of the argument.

Comments on the Quality of English Language

The quality of the English language in this paper is low. The authors should improve the clarity and conciseness. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper is clearly written and well-organized. Nevertheless, the following contents need to be improved:

 

The abstract is too long, you should summarize it

 

The resolution of the figures needs to be improved

 

I recommend that in the related works section the authors present proposals where combinations of the GWO and PSO algorithms are used, instead of making a compilation of metatheuristic algorithms of another nature.  There are a large number of related works that you can analyzed, for example:

 

Zhang, X., Lin, Q., Mao, W., Liu, S., Dou, Z., & Liu, G. (2021). Hybrid Particle Swarm and Grey Wolf Optimizer and its application to clustering optimization. Applied Soft Computing101, 107061.

 

Alzubi, Q. M., Anbar, M., Sanjalawe, Y., Al-Betar, M. A., & Abdullah, R. (2022). Intrusion detection system based on hybridizing a modified binary grey wolf optimization and particle swarm optimization. Expert Systems with Applications204, 117597.

 

There is a typo in Table 2 “paramters”

 

I recommend comparing the results with other works based on the combination of GWO and PSO, since the section is very limited, the section presents only a comparison with a work by the same authors, which was not compared at the time with other combination variants.

 

The main problem I find in the work is that I cannot find any mathematical basis or demonstration that validates the proposed algorithms, which is why the research is very limited.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The Discussion section can be improved. For example, the three proposed approaches should be compared with numbers like loop estimations, etc. Also, the authors can compare the three approaches in this paper with other relevant research results.

Author Response

Dear Reviewer,

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

he authors have addressed my comments. 

Author Response

Comment 1: The authors have addressed my comments

Response 1: Thanks to the reviewer. No further comments are required by the reviewer.

Back to TopTop