Next Article in Journal
CFE-YOLOv8s: Improved YOLOv8s for Steel Surface Defect Detection
Previous Article in Journal
Clustering Network Traffic Using Semi-Supervised Learning
Previous Article in Special Issue
Enhancing Motor Imagery Electroencephalography Classification with a Correlation-Optimized Weighted Stacking Ensemble Model
 
 
Article
Peer-Review Record

Trial of Brain–Computer Interface for Continuous Motion Using Electroencephalography and Electromyography

Electronics 2024, 13(14), 2770; https://doi.org/10.3390/electronics13142770
by Norihiko Saga 1,*, Yukina Okawa 1, Takuma Saga 1,2, Toshiyuki Satoh 3 and Naoki Saito 4
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Electronics 2024, 13(14), 2770; https://doi.org/10.3390/electronics13142770
Submission received: 5 May 2024 / Revised: 4 July 2024 / Accepted: 8 July 2024 / Published: 15 July 2024
(This article belongs to the Special Issue Brain Computer Interface: Theory, Method, and Application)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper presents a BCI method for fast classification, offering detailed explanations in the introduction, methods, and discussions. However, there are several areas in the method section that require improvement. Firstly, for the EMG signal, a sampling rate of 500Hz is used, although most current EMG systems recommend a sampling rate of 1KHz or even higher, as there is still relevant information beyond 250Hz. Additionally, the only signal processing method mentioned is RMS followed by a 1Hz low-pass filter. It is well-known that the most significant noise in EMG signals is powerline noise and motion artifact. Most processing methods typically include filters to eliminate these signals before processing the EMG signal. However, the method described in the paper does not provide any information about this crucial step. The output of the RMS and 1Hz low-pass filter could be highly influenced by motion artifact, leading to less accurate ground truth for EEG. Several papers on EMG to Force conversion provide detailed methods in this regard. Lastly, in the results section, there is no statistical analysis, and the conclusions are unclear from Table 1 and Figure 8. More detailed explanations are needed to better present the method and its outcomes.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The study was conducted systematically and written the manuscript very well.

The following minor corrections may be incorporated:

1. Please include the Novelty (As a separate paragraph) and Contributions (in Bullet points) of the study at the last paragraph of the Introduction.

2. Please include the demographic information of the participants in a Table

3. Discussion section has to elaborated by including the main inferences of the results.

4. Since EEG signals are Non-linear, discuss the usage of non-linear signal processing methods mentioned in following paper and cite in the references: Nonlinear Signal Processing Methods for Automatic Emotion Recognition Using Electrodermal Activity

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Nice paper, nice topic, nice figures. Interesting and good-designed experiment; the research area seems to be a good choice for citability of the research. I do not fully understand why you publish in "MDPI Electronics" and not in "MDPI Brain Sciences", but that is your choice. Both are Open Access, so maybe it makes no big difference in the internet era.

The paper is relatively well-structured (as for me) - some introduction, some literature research, methodology, discussion, conclusions.

However, I have some minor comments:

1) The abstract is not useful at all. Your abstract is a miniature introduction, about history, about background, about motivation... - and only one line ("continuous movements can be captured by adding EMG to EEG") is a real abstract. Please make sure in your future papers, that the abstract should be a miniature paper (what, how, results, conclusion/impact), and/while the abstract is often included in databases as a searchable text, so the content of abstract really is important.

2) something is wrong in your text editor regarding splitting the words at the end of lines - I can see within text words cut in parts: "in-volved", "appli-cat-ions", "magne-toencephalography", "There-fore".

3) References include 4 papers of your authorship. That is risky, while the reviewers can reject the paper basing on "did you detect inappropriate self-citations by authors? yes/no" (as the "inappropriate" is not defined in reviewers form)

4) The idea of EEG+EMG is not new, it is very old, so do not try to convince anyone that it is new or innovative. But you don't, so that's good.

Overall evaluation - nice paper. Have a great career :-)
Reviewer.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors have satisfactorily addressed my concerns.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop