Application of Support Vector Machine Algorithm Incorporating Slime Mould Algorithm Strategy in Ancient Glass Classification

Round 1

Reviewer 1 Report

In this study, the dataset of the glass chemical composition was examined by optimizing the parameters of the support vector machine and the slime mold approach was used for the classification model. The results of the proposed algorithm are compared with the results of widely used classification models. The topic is original and address a specific gap. An effective classification technique for the selected subject has been brought to the literature.

The introduction part should be expanded. In particular, it should be emphasized in more detail why the classification of glass products is needed. A literature review should be done.

Discussion and conclusion sections are insufficient. It should be made more comprehensive.

Author Response

Please see the attachmen

Author Response File: Author Response.pdf

Reviewer 2 Report

I would like to bring these observations and comments to the attention of the authors:

1. In the abstract, in second sentence, did you mean "imported abroad"?

2. Line 14: There is sentence starting "so it is better..." you need to capitalize the first character. The same is on the line 354 "it is clear...".

3. In the abstract you are saying that you have 100% accuracy. There is danger that you've probably massively overfit. Did you perform cross-validation? If yes, it would be good to mention it in the paper.

4. Line 47: there is a sentence ending with "ancient glass items[1-4]." There should be space between "item" and "[1-4]" (and thus it would be necessary to apply it to the whole paper).

5. Line 89: High-dimensional data are defined as data in which the number of features (variable observed) p, are close to or larger than the number of observations (or data points), n. Is it in your case?

6. Informative value of image 2 and 6 is low, I suggest to remove them. On the other hand may be just for illustrative purpose you can insert into the paper photographs of ancient glass.

7. There should be text between two headings, for example 2 and 2.1 on lines 84, 85.

8. There is heading 2.1.1 on line 97 and immediatelly on next line there is heading 2.1.1 (should it be 2.1.1.1?) and others consecutive heading should be also headings of the fourth level?

9. On line 134 there are two words "are are" consecutively.

10. On line 171 there is sentence "It is possible to use supervised learning algorithms to regression analysis, classification research, and other domains." can you specify other domains more? Or reconsider.

11. I suggest to shrink the Figure 7.

12. On line 289 (page 9) and 337 (page 11, section 4): Very likely you mean "Precision" not "Accuracy".

13. Figure 8: How was this fitness function defined? What is the meaning of the blue resp. red curves? It would be good to specify it in the paper.

14. Line 322: There is text "We compareed", it should be "we compared".

15. There is not clear from the paper how the parameters in the table 2 for individual machine-learning algorithms and GA were determined and selected.

16. In the conclusion you are saying "it is clear that the chemical composition of ancient glass artefacts from around the world is similar." Is it that easy to conclude this? I think it would be better if you will back up this by citation of the source, although citations in conclusions are not very good idea.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf