Review History

All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.

Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.

View examples of open peer review.


  • The initial submission of this article was received on October 13th, 2020 and was peer-reviewed by 2 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on November 26th, 2020.
  • The first revision was submitted on January 6th, 2021 and was reviewed by 1 reviewer and the Academic Editor.
  • A further revision was submitted on March 6th, 2021 and was reviewed by the Academic Editor.
  • The article was Accepted by the Academic Editor on March 8th, 2021.

Version 0.3 (accepted)

· Mar 8, 2021 · Academic Editor


The concerns raised by reviewers have been attended and the paper is suitable for publication.

[# PeerJ Staff Note - this decision was reviewed and approved by Bob Patton, a PeerJ Section Editor covering this Section #]

Version 0.2

· Jan 25, 2021 · Academic Editor

Minor Revisions

Before acceptance, authors should have a careful revision of the English. The quality of figures should be also improved, as suggested by the first reviewer.

[# PeerJ Staff Note: The Academic Editor has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at for pricing (be sure to provide your manuscript number and title) #]

Reviewer 1 ·

Basic reporting

Thanks to the author.
The concerns raised in my previous review have been largely attended to.

Experimental design

No additional comments.

Validity of the findings

No additional comments.

Additional comments

No additional comments.

Version 0.1 (original submission)

· Nov 26, 2020 · Academic Editor

Major Revisions

The reviewers raised important criticisms which they described in detail. The manuscript requires extensive revision in order to be re-evaluated. It is advisable to reply to all the points raised by the 2 reviewers exhaustively.

[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.  It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter.  Directions on how to prepare a rebuttal letter can be found at: #]

[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at for pricing (be sure to provide your manuscript number and title) #]

Reviewer 1 ·

Basic reporting

The article is largely unambiguous and with sufficient background. The hypothesis and results are convincing to a large extent. Nevertheless, the author might consider reviewing the following.

Consider changing the sentence in lines 68-70 to "Particularly, a successful BCI primarily has two main requirements including a set of suitable electroencephalogram (EEG) features and an efficient machine-learning algorithm to classify the extracted features."

Also note that Transfer Learning does not apply only to CNN models or computer vision as implied in lines 76 and 164. It can be applied to other deep learning architectures.

Change "myriad" in line 111 to "several" or "a number of".

Please modify the statement, "It is worth noting that such a pipeline has yet been investigated with regards to wink-based EEG signals" in lines 114-115 to something like this: "It is worth noting that this is the first study to investigate such a machine learning pipeline with regards to wink-based EEG signals".

Change "till" in line 131 to "and".

Please delete "to transpire" in line 184.

Correct the spelling for "Inception" spelled as "Ineption" in Figure 5.

Experimental design

The technical and ethical standard of the work is acceptable. However, the methods need to clarified.

i) For instance, the method of transfer learning used was not fully described.
Were the retained pretrained layers' weights frozen or not during training of the classifiers? What is the justification for the approach adopted? E.g., performance reasons?

Further, there other clarifications that need to be provided to facilitate replication of results.

ii) What is the justification for the addition of RF classifier in the classification pipeline?
Was the performance of the TL models investigated in exclusion of the RF classifier?
What is the performance of the different TL models in that scenario?

iii) More so, you might want to check the performance of the RF classifier alone (i.e., in exclusion of TL).

The performance values realized from (ii) and (iii) could serve as a reference to demonstrate the benefit of the methods (combining TL and RF) applied in this study.

iv) Please include specificity and ROC AUC metrics to the performance evaluation metrics. In particular, It would be nice to consider specificity alongside the sensitivity values except the classes are balanced in the datasets.

Validity of the findings

The conclusion is in line with the aim of the study. However, clarification of the issues raised in the experimental design can improve the significance of findings.

Reviewer 2 ·

Basic reporting

A critical concern in this manuscript is that the authors used a very poor English to present. There are a lot of grammatical errors and typos. It is hard to follow and capture the ideas with poor English. Therefore, the authors should have an extensive revision on the English. It is important if it can be checked by a native speaker or English editing service.
Literature review are weak. The authors should show more latest works on the different feature extraction and classification techniques for EEG signals system.
Quality of figures should be improved. Now resolution is low.

Experimental design

The authors should release source codes for replicate the results.
How many experts were used for labeling? How to decide the experts?
Random algorithm has been used in previous works for classification of EEG. Thus the authors should refer more works to attract broader readership.

Validity of the findings

The authors have not compared their performance results with the previous works on the same problem. Therefore, it is not enough to convince the impact of the study.
The authors should have some independent tests on the model.
More discussions need to be added.

Additional comments

No comment.

All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.