Next Article in Journal
A User Study on Modeling IoT-Aware Processes with BPMN 2.0
Next Article in Special Issue
Intuitionistic Fuzzy Sets for Spatial and Temporal Data Intervals
Previous Article in Journal
An Optimized Deep Learning Approach for Detecting Fraudulent Transactions
Previous Article in Special Issue
Large-Scale Group Decision-Making Method Using Hesitant Fuzzy Rule-Based Network for Asset Allocation
 
 
Article
Peer-Review Record

Ensemble Modeling with a Bayesian Maximal Information Coefficient-Based Model of Bayesian Predictions on Uncertainty Data

by Tisinee Surapunt * and Shuliang Wang *
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Submission received: 12 March 2024 / Revised: 10 April 2024 / Accepted: 12 April 2024 / Published: 18 April 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Congratulations on submitting the manuscript to the MDPI journal. To improve the quality of the manuscript, the following suggestions should be considered:

1) I am not sure if the title would be written without BMIC, but with the full name it would be: "Ensemble Modeling with Bayesian Maximal Information Coefficient Based Model of Bayesian Predictions on the Uncertainty Data". Is it OK to write "Bayesian of Bayesian"? It is confusing.
2) It sounds very subjective, what is the uncertainty data and what is not, just looking at the description given in the Related works. Maybe authors could give some real examples, or data samples by showing and highlighting the differences. Or just to give some additional references by describing it, because now it looks like almost every dataset could be in some way described as uncertain if it is new and not analyzed before.
3) In my opinion the related works should be improved or rewritten. This section should present a literature analysis of similar scientific research. Now Authors provide definitions, introduce methods, etc., but there is no related works analysis. Some parts of this section could be moved to Section Methods.
4) There is no point in describing Bayesian so deeply, it is not a novelty, so it would be enough to write the main aims, usage, etc., instead of theorems.
5) I did not find any information or details about training, just the results obtained. If it is the combination of BMIC and classification algorithms (SVM, decision tree, etc), these models have been trained, so should be detailed presented the parameters and way how the models have been trained models. Need information about the dataset, about training parameters of classification algorithms, how the dataset has been split, etc. The authors state that data is not available because of privacy, but how to trust the results if no one knows how the models have been trained?

In my opinion, the authors need to improve the paper and present results by providing more details about experimental investigation.


Author Response

I appreciate you taking the time to review my manuscript. Please see my response in the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

See attached.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

None.

Author Response

I appreciate you taking the time to review my manuscript. Please see my response in the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Good luck with the final submission.

Reviewer 2 Report

Comments and Suggestions for Authors

The revised version of the manuscript addresses my concern and is recommended for publish.

Back to TopTop