The Application of Integration of EEG Signals for Authorial Classification Algorithms in Implementation for a Mobile Robot Control Using Movement Imagery—Pilot Study

Round 1

Reviewer 1 Report

This paper focused on the issue of recognition and classification of electroencephalographic signals. The signal measured and archived with a 32-electrode device was prepared for classification using a new solution consisting in EEG signal integration. The new waveforms modified can be processed using by both authorial software and an artificial neural network. The properly classified signals made it possible to use them as the signals controlling the LEGO EV3 Mindstorms robot. This research work is interesting for the signal processing research society. However, this paper has several limitations and the standard is not enough, and address the following items would result in a good paper,

 

1. The literature review is not thorough about the application and the contributions. To highlight the contributions, it suggests reorganizing the section of the related work. At least, for each contribution, it should be novel and meaningful according to a thorough literature review. In the literature analysis, it is recommended to read the following works and consider to discuss their similar application scenarios in the introduction and discussion, Improved recurrent neural network-based manipulator control with remote center of motion constraints: Experimental results;
2. It is recommended to present in the first section so that it can highlight the specific scope of this article. The meaning of the assessment experiment should be highlighted.
3. Maybe it is better to discuss the possibility to improve the scope using deep learning to learn and optimize in the introduction, for example, A Multimodal Wearable System for Continuous and Real-time Breathing Pattern Monitoring During Daily Activity; Multi-sensor Guided Hand Gestures Recognition for Teleoperated Robot using Recurrent Neural Network.
4. There should be a further discussion about the limitation of the current works, in particular, what could be the challenge for its related applications. To let readers better understand future work, please give specific research directions.
5. Figure 1 should be improved and labeled with more details. It is important to let the reader understand the application scenario from this figure. 

Author Response

Answear for Reviewer 1:

At the outset, as Authors, we would like to thank you very much for the factual and specific review. Below is a summary of the changes we have made to the article.

Reviewer: This paper focused on the issue of recognition and classification of electroencephalographic signals. The signal measured and archived with a 32-electrode device was prepared for classification using a new solution consisting in EEG signal integration. The new waveforms modified can be processed using by both authorial software and an artificial neural network. The properly classified signals made it possible to use them as the signals controlling the LEGO EV3 Mindstorms robot. This research work is interesting for the signal processing research society. However, this paper has several limitations and the standard is not enough, and address the following items would result in a good paper,

Authors:  In the above scope, we would like to thank you for your opinion. We fully agree.

1. The literature review is not thorough about the application and the contributions. To highlight the contributions, it suggests reorganizing the section of the related work. At least, for each contribution, it should be novel and meaningful according to a thorough literature review. In the literature analysis, it is recommended to read the following works and consider to discuss their similar application scenarios in the introduction and discussion, Improved recurrent neural network-based manipulator control with remote center of motion constraints: Experimental results;

Authors: Following your suggestion, we have expanded the Introduction to the article. We also expanded the literature review. We have introduced a new description for lines: 28-35, and also for lines 44-84. The changes made to the article are marked in blue.

1. It is recommended to present in the first section so that it can highlight the specific scope of this article. The meaning of the assessment experiment should be highlighted.

Authors: In this regard, we have expanded the Introduction to the article (lines 113-120). The changes made to the article are marked in blue.

1. Maybe it is better to discuss the possibility to improve the scope using deep learning to learn and optimize in the introduction, for example, A Multimodal Wearable System for Continuous and Real-time Breathing Pattern Monitoring During Daily Activity; Multi-sensor Guided Hand Gestures Recognition for Teleoperated Robot using Recurrent Neural Network.

Authors: In this regard, we have expanded the Introduction to the article (lines 64-84). The changes made to the article are marked in blue.

1. There should be a further discussion about the limitation of the current works, in particular, what could be the challenge for its related applications. To let readers better understand future work, please give specific research directions.

Authors: In this regard, we have expanded the Conclusions and Future Work in the article. The changes made to the article are marked in blue.

1. Figure 1 should be improved and labeled with more details. It is important to let the reader understand the application scenario from this figure. 

Authors: Figure 1 has been updated with a photo of the measuring station. In addition, we would like to point out that more details of the system measurement are presented in Figure 3.

 

 

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors presented and evaluated their BCI system in this pilot study. Given that the study is just a pilot, I think that it could be published. However, the author should attempt to improve the quality of the Introduction and the Discussion of their manuscript. I provide below my comments: 

Comment 1: 

The introduction should be focused (without redundant references to the history and long past of EEG) on the utility and properties of EEG. See below 2 indicative papers: 1) Kaiser, D. A. (2005). Basic principles of quantitative EEG. Journal of Adult Development, 12(2), 99-104. 2) Pfurtscheller, G., & Da Silva, F. L. (1999). Event-related EEG/MEG synchronization and desynchronization: basic principles. Clinical neurophysiology, 110(11), 1842-1857."

 

Comment 2: Also, the introduction should provide information about the classification algorithms that have been used in BCI systems. See below an indicative paper: 

Lotte, F., Congedo, M., Lécuyer, A., Lamarche, F., & Arnaldi, B. (2007). A review of classification algorithms for EEG-based brain–computer interfaces. Journal of neural engineering, 4(2), R1.

Comment 3:  In introduction, the authors should mention other BCI systems (see below for papers). Also, the discussion of the authors' results should be discussed in relation to other BCI systems. See below for papers on OpenVibe and other BCI systems: 

Renard, Y., Lotte, F., Gibert, G., Congedo, M., Maby, E., Delannoy, V., ... & Lécuyer, A. (2010). Openvibe: An open-source software platform to design, test, and use brain–computer interfaces in real and virtual environments. Presence, 19(1), 35-53.

Lindgren, J., & Lecuyer, A. (2016). OpenViBE and other BCI software platforms. Brain–Computer Interfaces 2: Technology and Applications, 179-198.

Author Response

Answear for Reviewer 2:

At the outset, as Authors, we would like to thank you very much for the factual and specific review. Below is a summary of the changes we have made to the article.

Reviewer: The authors presented and evaluated their BCI system in this pilot study. Given that the study is just a pilot, I think that it could be published. However, the author should attempt to improve the quality of the Introduction and the Discussion of their manuscript. I provide below my comments: 

Authors:  In the above scope, we would like to thank you for your opinion. We fully agree.

Comment 1: 

The introduction should be focused (without redundant references to the history and long past of EEG) on the utility and properties of EEG. See below 2 indicative papers: 1) Kaiser, D. A. (2005). Basic principles of quantitative EEG. Journal of Adult Development, 12(2), 99-104. 2) Pfurtscheller, G., & Da Silva, F. L. (1999). Event-related EEG/MEG synchronization and desynchronization: basic principles. Clinical neurophysiology, 110(11), 1842-1857."

Authors:  You're right, we've removed redundant historical references. We focused on the usefulness and properties of the EEG. We referred to your preferred publications - items 7 and 8 in the literature. The changes made to the article are marked in blue.

Comment 2: Also, the introduction should provide information about the classification algorithms that have been used in BCI systems. See below an indicative paper: 

Lotte, F., Congedo, M., Lécuyer, A., Lamarche, F., & Arnaldi, B. (2007). A review of classification algorithms for EEG-based brain–computer interfaces. Journal of neural engineering, 4(2), R1.

Authors:  We've added information about classification algorithms. The changes made to the article are marked in blue. We referred to the reference you proposed - currently it is no. 10 - Lotte, F. et al.

Comment 3:  In introduction, the authors should mention other BCI systems (see below for papers). Also, the discussion of the authors' results should be discussed in relation to other BCI systems. See below for papers on OpenVibe and other BCI systems: 

Renard, Y., Lotte, F., Gibert, G., Congedo, M., Maby, E., Delannoy, V., ... & Lécuyer, A. (2010). Openvibe: An open-source software platform to design, test, and use brain–computer interfaces in real and virtual environments. Presence, 19(1), 35-53.

Lindgren, J., & Lecuyer, A. (2016). OpenViBE and other BCI software platforms. Brain–Computer Interfaces 2: Technology and Applications, 179-198.

Authors:  We mentioned other BCI systems. We discussed the results against other BCI systems. The changes made to the article are marked in blue. In items 12 and 13, we referred to your preferred references: Renard, Y. – et al. and Lindgren, J. et al.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have addressed all of my concerns. No more revision is required from me. The current version can be accepted now. 

Reviewer 2 Report

The authors addressed effectively my comments. The manuscript appears to have an adequate quality for a pilot study. Hence, I endorse its publication.