Next Article in Journal
Critical Challenges and Potential for Widespread Adoption of Mass Timber Construction in Australia—An Analysis of Industry Perceptions
Previous Article in Journal
Seismic Performance of a Novel Precast Beam-Column Joint Using Shape Memory Alloy Fibers-Reinforced Engineered Cementitious Composites
 
 
Article
Peer-Review Record

Automatic Modeling for Concrete Compressive Strength Prediction Using Auto-Sklearn

Buildings 2022, 12(9), 1406; https://doi.org/10.3390/buildings12091406
by M. Shi 1,2 and Weigang Shen 1,*
Reviewer 1: Anonymous
Reviewer 2:
Buildings 2022, 12(9), 1406; https://doi.org/10.3390/buildings12091406
Submission received: 14 July 2022 / Revised: 18 August 2022 / Accepted: 31 August 2022 / Published: 7 September 2022
(This article belongs to the Section Building Materials, and Repair & Renovation)

Round 1

Reviewer 1 Report

1. The paper's title is not appropriate. It's extremely generic. It is preferable to include the approach's name in the title.

2. The authors discussed machine learning and soft computing in numerous sections of the paper.... To begin with, I would like to note that authors should use terminology consistently. In addition, rather than using these generic keywords, they should mention the approach directly.

3. In line 18, the authors make an unprofessional assertion. There are numerous rapid machine learning techniques!

4.  In the abstract, the research gaps should be highlighted.

5.  The paper's citation format should be revised. Please check the MDPI author's guidelines and modify the paper's citation format accordingly.

6. In the literature review, a few recent studies were overlooked. Please add the following articles to the soft computing methods for concert strength prediction. Shahmansouri, Amir Ali, et al. "Artificial neural network model to predict the compressive strength of eco-friendly geopolymer concrete incorporating silica fume and natural zeolite." Journal of Cleaner Production 279 (2021): 123697. And "The prediction analysis of compressive strength and electrical resistivity of environmentally friendly concrete incorporating natural zeolite using artificial neural network." Construction and Building Materials 317 (2022): 125876.

7. The first table is not comprehensive. Many studies are missing from this table.

8. The paper's contributions are presented in an unprofessional manner. They should clearly emphasise the paper's theoretical contributions. Please correct it.

9. The purpose of figure 1 is not clear to me. If the authors wish to use it as a roadmap for their research, it should be relocated to the research methods section and revised.

10. Please use the appropriate heading numbering system for data sets in section 2.1. The current model of representation is somewhat disorganised.

11. Figure 6's presentation should be revised.

12. The results sections are satisfactory.

 

13. Conclusions should address the limitations of the study and future research directions.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The study is very interesting and the paper can be published as it is.

Author Response

Thank you for your praise.

Reviewer 3 Report

Comments

1. The abstract and introduction should rewrite and follow the standard of the international articles, especially the introduction part. Try to avoid Tables and figures in the introduction part, and it seems the report of this submission, not articles. 

2. Methodology should be very specific, concise, and clear. It's difficult to understand the methodology. 

3. The results of the data need to be presented concisely and clearly. The author should compare each set of results with other existing research results. 

4. Conclusion should be more critical and in-depth. 

5. The English language should be checked through the paper.  

Comments for author File: Comments.docx

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Accept.

Back to TopTop