Stream Convolution for Attribute Reduction of Concept Lattices

Round 1

Reviewer 1 Report

The paper under review proposes a new approach to attribute reduction in concept lattices based on Convolutional Neural Networks (CNN). The authors identify several challenges with existing approaches, including limitations of incremental or decremental algorithms and a lack of research combining CNN with concept lattices.

However, there are some limitations that I want to point out:

* The paper does not provide a comprehensive review of existing deep learning-based approaches to attribute reduction in concept lattices.

* The focus of the related work section is on introducing the background and context of the proposed approach, rather than providing an exhaustive review of existing methods.

* This limits the ability to contextualize the contribution of the proposed approach and identify areas for future research.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

In abstract specify the results and core objective.

 How authors collected data must be clear?

 Literature review part is not adequate and must be improved.

 Method section is tough to understand, give explanation for all equations and give examples to show how the equations can be used.

 Comparison is weak and must include statistical and computational metric.

 Work on conclusion as it is weak for now, expand and explain results clearly, state the future scope in detail.

 What are the advantages and disadvantages of the work must be provided in discussion part?

Moderate editing is required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf