Meticulous Land Cover Classification of High-Resolution Images Based on Interval Type-2 Fuzzy Neural Network with Gaussian Regression Model
Round 1
Reviewer 1 Report
In this paper authors have proposed a meticulous land cover classification method that combines Gaussian regression model (GRM) with interval type-2 fuzzy neural network (IT2FNN) model as a classification decision model. My Review is as under.
1. Introduction part need to define a critical analysis of the literature and general diagram for better understandability of the readers.
2. Parameters used for simulations and analysis must be stated and referenced.
3. Figure 2. Classification decision model needs more explanation.
4. Write one paragraph at the end i.e., before conclusion to describe training data histogram.
Author Response
Dear Reviewers:
Thank you for your valuable comments and affirmation of the work of this article. Your suggestions are of great help in improving the quality of our articles. We have carefully answered the questions one by one in accordance with the reviewer's requirements, and have carefully revised the article. We restructured the article and checked for grammar issues. The revised manuscript is detailed in the attachment. Finally, I wish you the best of luck in your work.
kind regards,
All authors
Author Response File: 
Author Response.pdf
Reviewer 2 Report
About the paper: Meticulous Land Cover Classification of High-resolution 2 Images Based on Interval Type-2 Fuzzy Neural Network with 3 Gaussian Regression Model
- It is research that meets the scope of the Remote Sensing Journal.
- Suggestions:
(a) Abstract: This paper proposes a (meticulous) land cover classification method that combines
(b) Delete the lines 122 to 127.
(c) 4. Discussion: The authors continue to show the results. They need to compare their results with other works or discuss the differences between land cover classifications made for the same areas.
(d) [The phenomenon of "different gray value of the same 626 land", "similar gray value of different land"] - lines 626 to 627: I think it is a common problem in all supervised or unsupervised classifications. It is better to emphasize the similarities and differences with the more traditional methods.
(e) Lines 640 to 665: The authors highlight the development of satellite technology. And how remote sensing image classification has a relevant research value for urban planning. The suggestion is to improve this argument. It can focus on contributing to the regional land cover classification in a short time, guaranteeing better accuracy.
Author Response
Dear Reviewer:
Thank you for your valuable comments and affirmation of the work of this article. Your suggestions are of great help in improving the quality of our articles. We have carefully answered the questions one by one in accordance with the reviewer's requirements, and have carefully revised the article. We restructured the article and checked for grammar issues. The revised manuscript is detailed in the attachment. Finally, I wish you the best of luck in your work.
kind regards,
All authors
Author Response File: Author Response.pdf
Reviewer 3 Report
I have wondered whether the use of "meticulous" in the title in the end I decided that it is such an unusual word to see in a title it might attract readers ... but ... the downside is that the reader might expect something along the line of highly detailed.
I think the introduction might be improved by a slightly wider range of references, particularly the issue of why a smaller pixel can increase problems with identifying a land cover. I also think that more reference to the literature on image segmentation is needed in comparison to what is effectively a moving window used in this paper.
The maths has given me a bit of a headache ... the third equation in set 3 is as far as I can see the same as the first in set 4. I think a graphical representation might help clarify how the measures of fuzziness and uncertainty is generated.
The bounds of equation 8 seem wrong to me - is this a "typo"? (error in the type setting?) if not I don't follow why the bound 0.3 o 1 is being used (and hence needs more explanation in the text).
Author Response
Dear Reviewers:
Thank you for your valuable comments and affirmation of the work of this article. Your suggestions are of great help in improving the quality of our articles. We have carefully answered the questions one by one in accordance with the reviewer's requirements, and have carefully revised the article. We restructured the article and checked for grammar issues. The revised manuscript is detailed in the attachment. Finally, I wish you the best of luck in your work.
kind regards,
All authors
Author Response File: Author Response.pdf
