Next Article in Journal
First-Principles Investigation of Electronic and Related Properties of Cubic Magnesium Silicide (Mg2Si)
Next Article in Special Issue
Artificial Neural Network Model for Membrane Desalination: A Predictive and Optimization Study
Previous Article in Journal
Impact of Social Media on Knowledge of the COVID-19 Pandemic on Bangladeshi University Students
Previous Article in Special Issue
An Improved Multilabel k-Nearest Neighbor Algorithm Based on Value and Weight
 
 
Article
Peer-Review Record

Modeling and Forecasting of nanoFeCu Treated Sewage Quality Using Recurrent Neural Network (RNN)

Computation 2023, 11(2), 39; https://doi.org/10.3390/computation11020039
by Dingding Cao 1,2, MieowKee Chan 1,* and SokChoo Ng 3
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Computation 2023, 11(2), 39; https://doi.org/10.3390/computation11020039
Submission received: 6 January 2023 / Revised: 30 January 2023 / Accepted: 12 February 2023 / Published: 17 February 2023
(This article belongs to the Special Issue Intelligent Computing, Modeling and its Applications)

Round 1

Reviewer 1 Report

 

Modeling and Forecasting of Sewage Quality Using Recurrent  Neural Network (RNN)

Corrections

1.    There are a lot of comments during Pdf version need to discussed

2.    The abstract needs to we-write

3.    I suggest to design an ideal scheme  system  to simulate  three to three model (input , hidden , output)

4.    Suggest to write an table to show the differences results between the one – to three model

5.    Its notices that the authors concentrate more about the correlation coefficient between its model .. the authors needs to discuss more about for example why nitrile is more efficient than others .

6.    First reference in the reference list was wrong .

Comments for author File: Comments.pdf

Author Response

We made the amendments to the manuscript according to the reviewer's comments. Kindly refer to the attachment. 

Author Response File: Author Response.docx

Reviewer 2 Report

In the present work, the authors developed a recurrent neural network to estimate the removal of specific species from sewage using nanoFeCu. The results demonstrate that their three-to-three model is effective at performing the task and outperforms the one-to-one model, given the species' presences are strongly correlated. The authors provided a survey of earlier relevant works in the introduction section and properly cited the references. The main work is clearly presented and self-consistent.   Other comments include: Line 162 (Table 2): how is flow rate data relevant and incorporated into the model?   line 185 (Table 3): please justify the choice of 1000 iterations.    Line 187 (Figure 1): this does not look like the typical RNN architecture. Also, please specify what is used as the input and what the output is for that specific input.

Author Response

We made the amendments to the manuscript according to the reviewer's comments. Kindly refer to the attachment. 

Author Response File: Author Response.docx

Reviewer 3 Report

The article concerns the modeling and forecasting of sewage quality. It may be interesting for readers of Computation. In general, this manuscript is well organized and written. The following requests/suggestions should be taken into account to improve the quality of the manuscript.

-  Please change the title. The article refers to the selected method of sewage treatment: the use of nanoFeCu in treating sewage.

-  Please explain why the focus was only on the study of nitrogen forms in wastewater.

-  Why do you contribute to the progress of science? How is analyzed sewage treatment process currently controlled? Please explain this issue in the Introduction.

-  Sewage quality variability is very important in the analysis of sewage quality. I propose to present the results graphically using the box and whisker plot.

-  What are the limitations of the proposed model? Are there plans to conduct research on a larger scale using other sewage? Please refer to this issue in the Conclusions.

-  Equations (4) – (10) should be moved to point 3.3.

Author Response

We made the amendments to the manuscript according to the reviewer's comments. Kindly refer to the attachment. 

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

All suggestions/observations/requirements were implemented according to my comments. All the best. 

Back to TopTop