Classification of Post-COVID-19 Emotions with Residual-Based Separable Convolution Networks and EEG Signals
Round 1
Reviewer 1 Report
This study aimed to propose a DL approach for Emotional Valence Recognition with eeg signals. I have the following suggestions.
What is the novelty of this study although several ML/DL approaches for Emotional Recognition with eeg signals have been proposed?
Several figures are not readable in pdf available to reviwers.
EEG is highly sensitive to the powerline, muscular, and cardiac artifacts. In EEG data preprocessing, authors need to mention how you handle AC power, ECG, and EMG artifacts in EEG signals. Same for EOG, EMG and others. Do the authors think that their proposed method is robust to such kinds of artifacts?
Please write down the contribution of the study at the end part of the Introduction section in bulleted form.
Authors should improve the conceptual figures of their DL proposed frameworks with more details and model parametrization.
What is the epoch length of EEG signal? Few figures are not easy to read and quality need to improve.
Authors should introduce the EEG applications in ML-based disease, and mental workload prediction in broad scope, such as article, Explainable Artificial Intelligence Model for Stroke Prediction Using EEG Signal; in article, healthsos: real-time health monitoring system for stroke prognostics; in article, quantitative evaluation of task-induced neurological outcome after stroke; in article, driving-induced neurological biomarkers in an advanced driver-assistance system; and in article, quantitative evaluation of eeg-biomarkers for prediction of sleep stages.
The authors need to mention the model parameters or hyperparameters of DL models. The performance of the model is dependent on the selection of the architecture and/or parameters.
Authors should report more performance measures of classifiers, such as sensitivity, specificity, precision, and negative predictive value from the confusion matrix.
How authors can prove that emotions during Covid19 are independent than non-Covid19?
Both cross-validated training and testing ROC curves of all emotion classes.
How did the authors deal with dataset class imbalance challenges in DL analysis?
I recommend to use deepSHAP/Grad-CAM to explain the contribution of EEG features in DL model.
The discussion section needs to be included. Authors must make discussion on the advantages and drawbacks of their proposed method with other studies adding a table in the discussion section.
Clinical explanation of these findings needs to be described in support of reference.
Author Response
Original Manuscript ID: sustainability-2117427
Original Article Title: Classification of Post-Covid19 Emotions by Residual-based Separable Convolution Networks and EEG Signals
To: Editor in Chief,
Sustainability, MDPI
Re: Response to reviewers
Dear Editor,
Many thanks for insightful comments and suggestions of the referees. Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with yellow highlighting indicating changes, and (c) a clean updated manuscript without highlights (PDF main document).
By following reviewers’ comments, we made substantial modifications in our paper to improve its clarity and readability. In our revised paper, we represent the improved manuscript.
We have made the following modifications as desired by the reviewers:
Best regards,
Corresponding Author,
Dr. Abdul Rauf Baig (On behalf of other author),
Professor.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
1. Can you change your title to:
An Automatic Classification of Post-Covid19 Emotions by Residual-based Separable Convolution Networks
References should be in the same format.
2. Three of your references lack volumes, issues, pages, or published years. Please add the volume number, issue number, page number, or published year. E. g. References 1,14,40.
3. Regarding the name of a journal or a conference, the initial letter of each notional word of the journal or conference name should be capitalized. E. g. References 13,51.
4. Please provide the italic and full name of the journal. E. g. Reference 51.
5. ALL Abbreviations should be defined in full the first time they appear in the title, abstract, main text, and figure or table captions, even if they are well-known in the field
The first time you use an abbreviation in the text, present both the spelled-out version and the short form.
The syntax is: The fully spelled out name (abbreviation)
For example KNN, DSC, and EFB. Please check for all other abbreviations in your manuscript.
Author Response
Original Manuscript ID: sustainability-2117427
Original Article Title: Classification of Post-Covid19 Emotions by Residual-based Separable Convolution Networks and EEG Signals
To: Editor in Chief,
Sustainability, MDPI
Re: Response to reviewers
Dear Editor,
Many thanks for insightful comments and suggestions of the referees. Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with yellow highlighting indicating changes, and (c) a clean updated manuscript without highlights (PDF main document).
By following reviewers’ comments, we made substantial modifications in our paper to improve its clarity and readability. In our revised paper, we represent the improved manuscript.
We have made the following modifications as desired by the reviewers:
Best regards,
Corresponding Author,
Dr. Abdul Rauf Baig (On behalf of other author),
Professor.
Author Response File: Author Response.pdf
Reviewer 3 Report
Thank you for the opportunity to review a really important work in the post COVID 19 scientific scenario.
My comments are to be taken as suggestions for improvement for a really interesting work.
-Review the Figure Layout:
Figures 6, 7, 8 which are incomprehensible now.
-Create more explanatory abstract by including research aim
-The Introduction seems a bit unconnected in content the theoretical framework part and the link with the methodology used need to be deepened. Better defining aim of the research.
-To make the Literature review clearer put a summary table with the papers considered
-Specify details of data acquisition and methodology, sample
Author Response
Original Manuscript ID: sustainability-2117427
Original Article Title: Classification of Post-Covid19 Emotions by Residual-based Separable Convolution Networks and EEG Signals
To: Editor in Chief,
Sustainability, MDPI
Re: Response to reviewers
Dear Editor,
Many thanks for insightful comments and suggestions of the referees. Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with yellow highlighting indicating changes, and (c) a clean updated manuscript without highlights (PDF main document).
By following reviewers’ comments, we made substantial modifications in our paper to improve its clarity and readability. In our revised paper, we represent the improved manuscript.
We have made the following modifications as desired by the reviewers:
Best regards,
Corresponding Author,
Dr. Abdul Rauf Baig (On behalf of other author),
Professor.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Thank you for review responses. Although most of the review comments were not addressed.
1. No novelty has been proven.
2. This study is just an emotion classification. No relation with covid-19 has been found.
3. Authors must follow the state-of-art procedure of biomedical signal processing. No non-EEG artifacts were removed from EEG signal in this study. If EEG is corrupted with other artifacts and noise, DL model can’t remove artifacts bias in EEG signal. This study is biased with eye-blink, EMG ECG artifacts.
4. Authors didn’t understand comment#6. This study lacks domain-specific information. EEG data specification and preprocessing methods were not reported.
5. Literature review is not rich. All other comments must be addressed with care.
6. No hyperparameters are reported for Residual-based Separable Convolution Networks used in this study.
7. No clear pattern of EEG spectrogram seen in Grad-CAM for each emotion class.
8. Classification accuracy is very low. What is the motivation to propose this model?
9. Most of the figures are not clear to read.
Author Response
Original Manuscript ID: sustainability-2117427
Original Article Title: Classification of PostCovid19 Emotions by Residual-based Separable Convolution Networks and EEG Signals
To: Editor in Chief,
Sustainability, MDPI
Re: Response to reviewers
Dear Editor,
Many thanks for insightful comments and suggestions of the referees. Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with yellow highlighting indicating changes, and (c) a clean updated manuscript without highlights (PDF main document).
Despite the comments, we have also improved the revised paper in terms of English writing style. By following reviewers’ comments, we made substantial modifications in our paper to improve its clarity and readability. In our revised paper, we represent the improved manuscript.
We have made the following modifications as desired by the reviewers:
Best regards,
Corresponding Author,
Dr. Abdul Rauf Baig (On behalf of other author),
Professor.
Author Response File: Author Response.pdf
