Distributed Fuzzy Cognitive Maps for Feature Selection in Big Data Classification

Round 1

Reviewer 1 Report

1. What do you mean by an integral role?

2. In abstract, you mentioned decision making. What decision making task was considered in this work?

3. The scope of the paper is unclear. It is needed to add a section of problem formulation to described formally the scientific problem that is studied. 

4. All the assumptions needed should be summarized.

5. It is recommended to discuss over existing methods in "A review on soft sensors for monitoring, control and optimization of industrial processes.

6. On page 9 there are two Figure 5. Why? The legend is too small to read.

7. English writing needs editing. Consistency is needed throughout the manuscript. For example, Big Data and big data.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript presents atechnique for feature selection in big data based on some well-known techniques. However the combination of these methods seems to be unique for this application. Therefore the authors should be more clear and better stress the novelty of their work . The following comments are given to further improve the manuscript quality:

1.    Avoid lumping references, e.g. 13-15 and similar. Instead summarize the main contribution of each referenced paper in a separate sentence and/or cite the most recent and/or relevant one.

2.    The authors should more clearly explain why they use those classification algorithms to evaluate the proposed model and why they are more accurate/suitable than some others. Have they tested any other?

In overall the contribution of the manuscript is acceptable but it still needs a minor revision.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Regarding the abstract section, the author should write it in a way that explains the proposed work, and it is preferable to put some of the results he reached.

Section 1, The introduction is weak and needs to be rewritten and updated. The introduction section can be extended to add the issues in the context of the current work and how the proposed approach can be used to overcome this.

The contributions that the authors introduced should be listed in the last part of the introduction section

Some paragraphs in the text need references - I ask the author to review the paper well. More recent references must be included.

I also recommend reviewing the language in all parts of the paper

Section2, related Works - In this part, the author must address recent work and not only write a reference but explain what has been done and why the author has introduced his work.

What is the motivation for the proposed work? Research gaps and objectives of the proposed work should be clearly justified

Fig. 1 is not apparent - please redraw it in a simple way

The table numbering is incorrect. Please check it carefully

The difference between present work and previous Works should be highlighted

A sufficient explanation of some of the tables in the paper is missing, as is the case in some Figs in the paper

Figs 6 and 7 need revision

Need a detailed explanation of the preprocessing steps

Comparison with recent studies and methods would be valued.

The performance analysis section is missing  

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 4 Report

# Paper discusses the distributed fuzzy cognitive map-based learning which extracts the features from the dataset that play the most significant role in decision making. This is appreciated.

# Clearly, provide the bullet-wise "major contributions" for this paper at second last paragraph of the Introduction section.

# Add more comparative tables related to literature survey and used methodology for the title of this paper. Also, add Two figures/diagram based on work flow of the proposed methodology related to existing work in the same domain.

#Section 3 and Section 4 are very strong point in this paper and must be appreciated for the experimentation done to it.

# Add one more section before conclusion section as "Discussions" of this paper. This will improve the overall impact of this paper.

# Add more references and cite below article to improve the readability of your paper:
(1)Bunch graph based dimensionality reduction using auto-encoder for character recognition", Robin Singh Bhadoria, Sovan Samanta, Yadhunath Pathak, Piyush Kumar Shukla, Ahmad Ali Zubi, Manjit Kaur, Multimedia Tools & Applications (Springer), Vol.81, No. 22, pp. 32093–32115, 2022.

(2)"Prognostic Kalman Filter Based Bayesian Learning Model for Data Accuracy Prediction", S. Karthik, Robin Singh Bhadoria, Jeong Gon Lee, Arun Kumar Sivaraman, Sovan Samanta, A. Balasundaram, Brijesh Kumar Chaurasia, S. Ashokkumar, Journal Computers, Materials & Continua (CMC), Vol. 72, Issue 1, pp. 243-259, 2022.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

I found the revision satisfactory and suggest accepting the paper in its current form.