Predictions of the Key Operating Parameters in Waste Incineration Using Big Data and a Multiverse Optimizer Deep Learning Model
Round 1
Reviewer 1 Report
Please see the attached file.
Comments for author File: 
Comments.pdf
Extensive editing of English language required.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
1) At the end of abstract, please add the numerical performance index in terms of prediction accuracy to justify the effectiveness of the proposed MVO-SVM based method.
2) The justification of adopting multiverse optimizer in this paper is not clearly stated, while there are thousand more of metaheuristic based optimizer nowadays. The can justify it by providing the merits of MVO as well as the application of MVO in parameter estimation and modelling, such as:
[a] https://doi.org/10.3390/en12112158
[b] https://doi.org/10.1016/j.apm.2021.01.023
[c] https://doi.org/10.2166/hydro.2023.126
[d] https://doi.org/10.1002/tal.1777
[e] https://doi.org/10.1109/IAEAC.2018.8577808
3) The procedure to apply MVO in tuning the SVM seems not clear. Please add additional step-by-step procedure to apply MVO to tune C and \sigma parameters of SVM. Please show the relation of universe position x_i with the parameter [C, \sigma] and the relation of the objective function in MVO and the objective function of the problem (RMSE?).
4) It is suggested to reorganize the usage of symbols since there are some redundant symbols. For example, symbol x represents universe in MVO and also represents historical observation in the Equation 5.
5) Table 7 is missing in this paper while there are several incomplete sentence after Table 7. Please carefully check the whole paper before submit to the editorial system.
6) The results and analysis still not sufficient to justify the effectiveness of the MVO-SVM. Since MVO is stochastic in nature, the author should perform the statistical analysis of the RMSE as well as including the Wilcoxon sign rank test in comparison with BAS-SVM and PSO-SVM.
7) There are too many typos in this manuscript. It is suggested to submit this article to native English proofreader before submit the revised version to the editorial system.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
There are some issues that badly affect the results of the proposed method, which are summarized as follows:
1. The authors did not pay attention to the correlation between 14 variables.
2. Cointegration issue is not considered.
3.Did the authors check 3 output variables correlated? Please discuss it.
There are issues that could affect the results of the analysis. So major revision is given.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Thank you for your answers.
English language fine
Author Response
Thank you for your comments and suggestions.
Reviewer 2 Report
The authors have carefully addressed all the comments, except for the following points:
1) There are many applications of MVO in the parameter estimation and modelling problems that are not reported in the literature of this paper. Therefore, please add several more references on recent applications of MVO to the parameter estimation and modelling problems as suggested in the previous comments.
2) The presented Wilcoxon rank test in this paper is somehow not appropriate. The p-value is obtained after we compare the statistical value of objective function between two algorithms. However, in Table 8, the data is too confusing. The reader is not clear which kind of algorithm is being compared. Moreover, the organization of Table 8 should be revised since there are combining of 10 rounds as well.
3) Please add additional step-by-step procedure to apply MVO to tune C and \sigma parameters of SVM. Please show the relation of universe position x_i with the parameter [C, \sigma] and the relation of the objective function in MVO and the objective function of the problem.
4) Some figures are cut and not properly drawn. In addition, some tables are too wide and going beyond the given indent. Please re-locate the figures and tables properly.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
All issues are well-responded, so it can be accepted as it is.
Author Response
Thank you for your comments and suggestions.
Round 3
Reviewer 2 Report
The authors have carefully addressed all the comments. However, there are still minor correction in terms of the arrangement of Tables and Figures. Some tables and figures are beyond the given indent and the size is not appropriate. Please rearrange again the size of Tables and Figures.
Author Response
All figures and tables have been carefully proofread according to the template file, thanks for the suggestion!
