A Novel Simplified Convolutional Neural Network Classification Algorithm of Motor Imagery EEG Signals Based on Deep Learning

Round 1

Reviewer 1 Report

Authors of the work “A Novel Simplified Convolutional Neural Network Classification Algorithm of Motor Imagery EEG Signals Based on Deep Learning” propose in this paper an algorithm that combines continuous wavelet transform (CWT) and simplified convolutional neural network (SCNN) to improve the recognition rate of MI-EEG. Using the CWT, the MI-EEG signals are mapped to time-frequency image signals.

Overall, it is a well-structured paper; the introduction section is wide and presents the purpose of the research in detail. There is a comparison and evaluations of the proposed method, using proper figures and showing up the proofs of the experiments included in the paper.

Although the proposal is interesting and within the scope of the Applied Science, there are different issues that should be addressed in order to improve the work.

[Minor comments]

• The abstract is very small and and may further detail the importance of right and left hand motor image electroencephalogram (MI-EEG) recognition
• Some references may be updated. Within the last 5 years).
• It is not specified how it has been designed or which framework has been used in the CWT-SCNN.
• The results shown in the Experimental Process and Results section would be scientifically supported if any statistical tests were applied. You still need to report (i) sample size, (ii) alpha value, and clearly state the null and alternative hypotheses. In order to improve the comparative, It would be interesting to look how this is done in the following paper, 4.1 section (it is an example…):
  • González-Briones, A., Villarrubia, G., De Paz, J. F., & Corchado, J. M. (2018). A multi-agent system for the classification of gender and age from images. Computer Vision and Image Understanding.
• The conclusion is also very small and does not meet the requirements for conclusions of the work.
• The used English is correct.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper presents the problem in an interesting way. It concerns current problems in the field of Motor Imagery. The Authors skilfully referred to deep learning in it.

The Authors discuss the current literature in detail in this topic.

The data set has been correctly selected. Data analysis was conducted based on, among others known wavelet analysis. The results obtained are interesting.

The proposed new algorithm as part of the study fulfills its task.

Recommended modifications:

1. Authors should also refer to mathematical formulas identifiers in the text.

2. In Conclusions one could only extend the applications for future plans in this area to save them to a greater extent than is currently the case.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf