Next Article in Journal
People with High Perceived Infectability Are More Likely to Spread Rumors in the Context of COVID-19: A Behavioral Immune System Perspective
Previous Article in Journal
Toxicity Rank Order (TRO) As a New Approach for Toxicity Prediction by QSAR Models
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
IJERPH
Volume 20
Issue 1
10.3390/ijerph20010702
Review Report
ijerph-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Prediction of Cavity Length Using an Interpretable Ensemble Learning Approach

Int. J. Environ. Res. Public Health 2023, 20(1), 702; https://doi.org/10.3390/ijerph20010702
by Ganggui Guo 1, Shanshan Li 2, Yakun Liu 1,*, Ze Cao 1 and Yangyu Deng 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Int. J. Environ. Res. Public Health 2023, 20(1), 702; https://doi.org/10.3390/ijerph20010702
Submission received: 4 December 2022 / Revised: 27 December 2022 / Accepted: 27 December 2022 / Published: 30 December 2022
(This article belongs to the Section Environmental Science and Engineering)

Round 1

Reviewer 1 Report

In this manuscript, the authors performed 10-fold cross-validation to select the optimal input configuration. The hyperparameters of three en-semble learning models — random forest (RF), gradient boosting decision tree (GBDT), and extreme gradient boosting tree (XGBOOST) — were fine-tuned by the Bayesian optimization (BO) algorithm to improve the prediction accuracy and compare the five empirical methods. The subject is very interesting. I am pleased to send you moderate comments. The results and theme of this paper is quite interesting. The layout is clear and easy to understand. Generally, this manuscript makes fair impression and my recommendation is that it merits publication in this Journal, after the following minor revision:

(1) The third paragraph of the introduction” In recent years, researchers start to put their focus on the interpretability of the ML models, which can bring significant improvement in the prediction accuracy [20].” A single reference is not sufficient here.

(2) What are the meanings of the symbols that appear in the paper?There should be a specific description. Such as in Eq.(2), What does the b mean? It is recommended that you make a symbolic description table.

(3) All the figures in this article are not clear enough, I hope they can be adjusted.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

This research provides a new kind of optimization algorithm and combination, and provides a new possibility and feasibility for the calculation and prediction of cavity length and related content.   

Formulas, figures and tables should be further improved by referring to the format specification of the journal, and the format of references should also conform to the specification.

In the part of analysis and conclusion, it is also necessary to emphasize and supplement the differences and connections with traditional algorithms and other methods.

 

 

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 3 Report

Detailed comments refer to the attachment.

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

Now this revision is acceptable.

Back to TopTop