Next Article in Journal
Exploring the Utility of Dutch Question Answering Datasets for Human Resource Contact Centres
Previous Article in Journal
Addressing Vehicle Sharing through Behavioral Analysis: A Solution to User Clustering Using Recency-Frequency-Monetary and Vehicle Relocation Based on Neighborhood Splits
 
 
Article
Peer-Review Record

Solving Decision-Making Problems Using a Measure for Information Values Connected to the Equilibrium Points (IVEP) MCDM Method and Zakeri–Konstantas Performance Correlation Coefficient

Information 2022, 13(11), 512; https://doi.org/10.3390/info13110512
by Shervin Zakeri * and Dimitri Konstantas
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Information 2022, 13(11), 512; https://doi.org/10.3390/info13110512
Submission received: 11 September 2022 / Revised: 24 October 2022 / Accepted: 25 October 2022 / Published: 27 October 2022

Round 1

Reviewer 1 Report

1.       What is the theoretical contribution of this research? It should be illustrated in the paper.

2.   The research problem isn’t being described clearly in the introduction section.

Author Response

Dear Reviewer,

Hello,

 

Thank you very much for the valuable and constructive comments. We agree that the problem statement and the contribution were not clearly depicted in the paper; hence we addressed these issues. In the following responses, the changes can be found.

We thank you again for your time and consideration.

 

Best regards,

Behalf of the authors,

Shervin Zakeri

 

PhD Fellow, Boursier

The Swiss Government Excellence Scholarships

Geneva School of Economics and Management

Information Science Institute (GSEM/ISI) &

Centre Universitaire d'Informatique (CUI)

Information Science Institute Battelle, Route de Drize 7

CH-1227 Carouge, Switzerland

Author Response File: Author Response.docx

Reviewer 2 Report

This paper proposed a new multi-criteria decision-making (MCDM) method, called a measure for information values connected to the equilibrium points (IVEP) method, and a new statistical measure for measuring the similarities of performances of the MCDM algorithms' outputs in a comparison process, called the Zakeri-Konstantas performance correlation coefficient. However, it still needs further improvement. I provide some suggestions below for the revised version:

1. In Page 3, the last line, “exist” in “There exist an MCDM method” should be “exists”. Please check the full paper.

2. In Page 4, the second line in section 2, “is” in “…method is developed to solve complex…” should be “are”.

3. In Page 4, line 11 in section 2, there is an extra space between “and” and “1”.

4. In Page 4, before Step 1, it is better to explain the input and output before introducing the algorithm.

5. Some related works lack of discussion, e.g., 1) Generalized divergence-based decision making method with an application to pattern classification; 2) A complex weighted discounting multisource information fusion with its application in pattern classification; 3) Negation of the quantum mass function for multisource quantum information fusion with its application to pattern classification.

6. In the section of application, please state clearly about the data source.

This work is interesting. I recommend accepting this paper after addressing the above revisions.

 

Author Response

Dear Reviewer,

Hello,

 

Thank you very much for the valuable and constructive comments. We tried our best to address the issues mentioned. In the following responses, the changes could be found.

We thank you again for your time and the consideration.

 

Best regards,

Behalf of the authors,

Shervin Zakeri

 

PhD Fellow, Boursier

The Swiss Government Excellence Scholarships

Geneva School of Economics and Management

Information Science Institute (GSEM/ISI) &

Centre Universitaire d'Informatique (CUI)

Information Science Institute Battelle, Route de Drize 7

CH-1227 Carouge, Switzerland

Author Response File: Author Response.docx

Reviewer 3 Report

The paper introduces a new multi-criteria decision-making method: measure for information values connected to the equilibrium points (IVEP). The paper also introduces a new statistical measure for similarities of performances of the MCDM methods' rankings. The introduced method is compared with other MCDA methods using a new Zakeri-Konstantas correlations coefficient and the Hamming distance.

 

The introduction provides a comprehensive review of existing entropy methods. The authors also provide a short review of existing MCDA methods which use different entropies. In the following sections, the authors introduce a new method and demonstrate how it works on real-life examples.

 

However, the paper is quite hard to follow, therefore its quality should be improved before the publication.

 

The list of suggestions is as follows:

  • Numbers style of citations should be used. E.g. [1] instead of one which is used in the paper.
  • The equations should be centered in the column of text.
  • Equations (16), (17) are hard to read. Please consider use \frac{}{} if latex or an alternative for word.
  • The tables are not formatted properly. Check the MDPI guidelines for the formatting.
  • Table 2 is hard to follow because of misaligned columns.
  • The quality of the figures should be improved. Values in figure 3 are unreadable because of the width of the orange bars. It is also hard to read because of the lack of a grid.
  • Figure 4 is unreadable. Turn it into a simple two-dimensional plot. There is no need to visualize those rankings in this way.
  • I suspect that VIKOR ranking is wrong. It should be reversed. For the VIKOR ranking better alternatives got smaller values of the Q.
  • It would be nice to have a table with each ranking from figure 4.
  • Enumeration of the similarity measures misses the two most suitable for decision-making: Weighted Spearman and WS rank similarity.
  • Most measures have values from -1 to 1.
  • As far as I can see, there is a lack of description of the properties of ZK coefficient. Is it symmetrical or not? What about the domain? Is it [-1, 1] or [0, 1]?
  • Figures 5 and 6 are hard to read. Consider remaking them as flat bar plots.
  • Consider moving section 4.1 so the results of the comparison and propositions of the new methods will not mix up.

 

The paper has an interesting contribution: the new MCDA method and the new similarity coefficient. However, the results and discussion are hard to follow, and most figures are hard to read. I recommend reconsidering after a major revision.

 

Author Response

Dear Reviewer,

Hello,

 

Thank you very much for the valuable and constructive comments. The template issues have been revised, and the charts have been changed to address the comments. Moreover, a new equation and some properties of the new coefficient have been added to the paper.

We thank you again for your time and consideration.

 

Best regards,

Behalf of the authors,

Shervin Zakeri

 

PhD Fellow, Boursier

The Swiss Government Excellence Scholarships

Geneva School of Economics and Management

Information Science Institute (GSEM/ISI) &

Centre Universitaire d'Informatique (CUI)

Information Science Institute Battelle, Route de Drize 7

CH-1227 Carouge, Switzerland

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

Thank you very much for improving the paper according to the reviewers' suggestions. However in my opinion, there are several shortcomings that should be improved before the manuscript is published:

 

  • In response, the authors stated that bars in Figure 3 could not be fitted because of nine alternatives. However, it works perfectly in Figure 2, where all nine bars are perfectly fitter. Please, try to fix A1 bar, which overlaps other bars. Also, EP points are misplaced (it looks good in the previous version of the manuscript).
  • In my opinion, Table 2 should be split into two tables. In SaÅ‚abun's paper, the columns show the changes in the ranking and the coefficient values for those rankings, which is consistent. Table 2 in the revised manuscript shows criteria and alternatives in one table, and the number of columns differs. In my opinion, it should be formatted as two separate tables.
  • The authors consider removing VIKOR's results from the paper, so it should also be removed from Figures 6 and 7.

I recommend accepting after a minor revision.

 

Author Response

Dear Reviewer,

Hello,

 

We thank you very much for the constructive comments. The comments significantly raised the quality of the paper.

To address your comments, the Figure 2 is revised. The tables have been separated. The errors in the figures (6,7) have been corrected by removing the VIKOR from the figures.

We thank you again for your time and consideration.

 

Best regards,

Behalf of the authors,

Shervin Zakeri

 

PhD Fellow, Boursier

The Swiss Government Excellence Scholarships

Geneva School of Economics and Management

Information Science Institute (GSEM/ISI) &

Centre Universitaire d'Informatique (CUI)

Information Science Institute Battelle, Route de Drize 7

CH-1227 Carouge, Switzerland

 

Author Response File: Author Response.docx

Back to TopTop