Mentor feedback of Paper 1:

Title of the paper: Resource provisioning towards OPEX optimization in horizontal edge federation

The critical analysis of the paper is being carried out very well by the reviewer. The prescribed structure is maintained covering all the points that shows the quantification, what is being done, and how it is done, and why it is important, are well mentioned and reviewed. I don't find any major weakness, but try to give numbering to your analysis, such that you can avoid confusion and can refer back to the comments you have made. The technical jargon and the language used were related to the subject and can be understood easily, as there is a flexibility of readability. I think so vivek you can add a point to cite new references needed also for this paper. Figures quality also must be enhanced indeed. This is an absolute and obvious review on methodology and results of it.

I feel so the above the positives, and few missing points of the review.

Dear Sir, thank you for your suggestions. I have reviewed one more paper, as per your suggestions, and I have incorporated every suggestion given by you. Please consider my request, and review it. Thank you.

Paper 2 Review:

Title: Predicting Consumer Preferences in Electronic Market Based on IoT and Social Networks using Deep learning-based Collaborative Filtering Techniques

The paper satisfies the journal guidelines.

The motivation for the proposed work is clearly stated and implemented.

The paper is well written with technical jargon wherever needed, and appropriate tables and figures are used aligned well as per the author guidelines.

The paper is readable and can be understood once readers understand the technical concepts of artificial intelligence and IoT.

The aim is clear to predict consumer preferences in social networks using techniques of IoT and deep learning.

The study has proved that the efficiency of the neighborhood-based collaborative filtering model (SN-CFM)

The title is appropriate as per the content. Research gaps, objectives, and proposed are clearly justified.

References are relevantly cited correctly as per the contents and are recent.

Some more information about horizontal edge federation can be given in the introductory part to get better understandings.

There is good literature in this area, thus I feel the author could be used good literature from the 2019 year.

The important aim is to propose deep learning with a collaborative filtering technique for the recommendation system for Predicting User preferences from the IoT devices and Social Networks that are beneficial for users based on their preferences in electronic markets.

Subject selection is clear, and Research objectives are clearly stated.

The proposed solution justifies the given research hypothesis.

The metrics are considered suitable to perform the simulations

Study methods compared and proposed are valid

Techniques in neighborhood-based collaborative filtering model to know the consumer's interest in the social networks that is used.

Use a simple diagram or figure to illustrate the whole idea of this paper, and the modification it has been made from previous work or traditional framework. However, the architecture needs detailed explanation

The study explains clearly its advantages with respect to the literature: it is clear what is the novelty and contributions of the proposed work.

The results need more explanations. Additional analysis is required at each experiment to show its main purpose.

Metrics like MAE, RMSE, PPV,Recall, MCC, and Accuracy are used, but the intention for using only these metrics is not specified.

The content is clear to understand in terms of equations, figures, and tables. But there are few grammatical issues I observed in the paper.

Results are appropriate to the proposed algorithm, and compressions and quantifications are perfect

The obtained results show that horizontal edge federation based on the FMFK performs better and serves more input requests comparing to the non-federation approach.

The proposed approach shows frameworks are acquainted with giving item recommendations to the clients dependent on processing the likenesses between the clients.

Results are compared to the existing ones and the number of runs

The effect of 7 factors is well examined and described in the paper using the collaborating filtering algorithms.

The findings also provide satisfactory results for the research proposed. The performance evaluation summary intrinsically elucidates all the required information.

The paper is scientifically sound, in terms of design, technique, and Results.

The novelty of this paper is clear. The difference between present work and previous Works are to be addressed.

They are no flaws in the article, as per my review. The article is good and consistent. The paper is technically sound, and I see all the aspects are incorporated into the paper. This shows clear readability of methods used and results in discussion, I wish the paper can be considered for the publication.