A solution to supervised motor imagery task in the BCI Controlled Robot Contest in World Robot Contest

Huixing Gou; Yi Piao; Jiecheng Ren; Qian Zhao; Yijun Chen; Chang Liu; Wei Hong; Xiaochu Zhang

doi:10.26599/BSA.2022.9050014

Brain Science Advances 2022, 8(2): 153-161 https://doi.org/10.26599/BSA.2022.9050014

Research Article |

Open Access | Issue | Published: 29 June 2022

A solution to supervised motor imagery task in the BCI Controlled Robot Contest in World Robot Contest

Show Author's Information Hide Author's Information Huixing Gou^{¹^,^§}, Yi Piao^{²^,^§}, Jiecheng Ren^¹, Qian Zhao^¹, Yijun Chen^¹, Chang Liu^¹, Wei Hong^¹, Xiaochu Zhang^{¹^,²}(

)

1 Key Laboratory of Brain Function and Disease, Chinese Academy of Sciences, School of Life Science, Division of Life Science and Medicine, University of Science & Technology of China, Hefei 230027, Anhui , China

2 Institute of Advanced Technology, University of Science and Technology of China, Hefei 30001, Anhui, China

^§ These authors contributed equally to this work.

Keywords:

electroencephalography, brain-computer interface, convolutional neural network, motor imagery, EEGNet

Cite this article:

Gou H, Piao Y, Ren J, et al. A solution to supervised motor imagery task in the BCI Controlled Robot Contest in World Robot Contest. Brain Science Advances, 2022, 8(2): 153-161. https://doi.org/10.26599/BSA.2022.9050014

Download citation

EndNote(RIS)

BibTeX

827

Views

Downloads

Citations

Crossref

N/A

WoS

N/A

Scopus

N/A

CSCD

Abstract Full text About this article

Abstract

Background:

One of the most prestigious competitions in the world is the World Robot Conference. This paper presents the winning solution to the supervised motor imagery (MI) task in the BCI Controlled Robot Contest in World Robot Contest 2021.

Methods:

Data augmentation, preprocessing, feature extraction, and model training are the main components of the solution. The model is based on EEGNet, a popular convolutional neural networks model for classifying electroencephalography data.

Results:

Despite the model’s lack of stability, this solution was the most successful in the task. The channels closest to the vertex were the most helpful in feature extraction.

Conclusion:

This solution is suitable for supervised MI tasks not only in this competition but also in future scenarios.

Full text

Abstract

Full text

Outline

About this article

A solution to supervised motor imagery task in the BCI Controlled Robot Contest in World Robot Contest

Show Author's information Hide Author's Information Huixing Gou^{¹^,^§}, Yi Piao^{²^,^§}, Jiecheng Ren^¹, Qian Zhao^¹, Yijun Chen^¹, Chang Liu^¹, Wei Hong^¹, Xiaochu Zhang^{¹^,²}(

)

2 Institute of Advanced Technology, University of Science and Technology of China, Hefei 30001, Anhui, China

^§ These authors contributed equally to this work.

Abstract

Background:

Methods:

Results:

Despite the model’s lack of stability, this solution was the most successful in the task. The channels closest to the vertex were the most helpful in feature extraction.

Conclusion:

This solution is suitable for supervised MI tasks not only in this competition but also in future scenarios.

Keywords: electroencephalography, brain-computer interface, convolutional neural network, motor imagery, EEGNet

References(19)

[1]

Oneuro Competition. https://oneuro.cn/n/competition/index (accessed Jun 16, 2022).

[2]

Wang Y, Cang S, Yu HN. A survey on wearable sensor modality centred human activity recognition in health care. Expert Syst Appl 2019, 137: 167-190.

DOI Google Scholar

[3]

Saeidi M, Karwowski W, Farahani FV, et al. Neural decoding of EEG signals with machine learning: a systematic review. Brain Sci 2021, 11(11): 1525.

DOI Google Scholar

[4]

Lotte F, Guan CT. Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans Biomed Eng 2011, 58(2): 355-362.

DOI Google Scholar

[5]

Sakhavi S, Guan CT, Yan SC. Learning temporal information for brain-computer interface using convolutional neural networks. IEEE Trans Neural Netw Learn Syst 2018, 29(11): 5619-5629.

DOI Google Scholar

[6]

Ak A, Topuz V, Midi I. Motor imagery EEG signal classification using image processing technique over GoogLeNet deep learning algorithm for controlling the robot manipulator. Biomed Signal Process Control 2022, 72: 103295.

DOI Google Scholar

[7]

Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. J Neural Eng 2019, 16(5): 051001.

DOI Google Scholar

[8]

Tang ZC, Li C, Sun SQ. Single-trial EEG classification of motor imagery using deep convolutional neural networks. Optik 2017, 130: 11-18.

DOI Google Scholar

[9]

Uktveris T, Jusas V. Application of convolutional neural networks to four-class motor imagery classification problem. Inf Technol Control 2017, 46(2): 260-273.

DOI Google Scholar

[10]

Milanés Hermosilla D, Trujillo Codorniú R, López Baracaldo R, et al. Shallow convolutional network excel for classifying motor imagery EEG in BCI applications. IEEE Access, 9: 98275-98286.

DOI Google Scholar

[11]

Chen JJ, Yu ZL, Gu ZH, et al. Deep temporal-spatial feature learning for motor imagery-based brain- computer interfaces. IEEE T Neur Sys Reh 2020, 28(11): 2356-2366.

DOI Google Scholar

[12]

Chen XG, Zhao B, Wang YJ, et al. Control of a 7-DOF robotic arm system with an SSVEP-based BCI. Int J Neural Syst 2018, 28(8): 1850018.

DOI Google Scholar

[13]

Chen XG, Huang XS, Wang YJ, et al. Combination of augmented reality based brain- computer interface and computer vision for high-level control of a robotic arm. IEEE T Neur Sys Reh 2020, 28(12): 3140-3147.

DOI Google Scholar

[14]

Romero DH, Lacourse MG, Lawrence KE, et al. Event-related potentials as a function of movement parameter variations during motor imagery and isometric action. Behav Brain Res 2000, 117(1/2): 83-96.

DOI Google Scholar

[15]

Machado S, Arias-Carrión O, Paes F, et al. Changes in cortical activity during real and imagined movements: an ERP study. Clin Pract Epidemiol Ment Health 2013, 9: 196-201.

DOI Google Scholar

[16]

Davidson RJ. EEG measures of cerebral asymmetry: conceptual and methodological issues. Int J Neurosci 1988, 39(1/2): 71-89.

DOI Google Scholar

[17]

Raffin E, Mattout J, Reilly KT, et al. Disentangling motor execution from motor imagery with the phantom limb. Brain 2012, 135(Pt 2): 582-595.

DOI Google Scholar

[18]

Wang F, Zhong SH, Peng JF, et al. Data augmentation for EEG-based emotion recognition with deep convolutional neural networks. In MultiMedia Modeling. Schoeffmann K, Chalidabhongse TH, Ngo CW, Eds. Cham: Springer, 2018, pp 82-93.

[19]

Hafez, M.B., Weber C, Kerzel M, et al., Efficient intrinsically motivated robotic grasping with learning- adaptive imagination in Latent space. In 2019 Joint Ieee 9th International Conference on Development and Learning and Epigenetic Robotics (Icdl-Epirob), Oslo, Norway, 2019, pp 240-246.

DOI Google Scholar

About this article

Publication history

Acknowledgements

Rights and permissions

Publication history

Received: 22 April 2022

Revised: 07 June 2022

Accepted: 10 June 2022

Published: 29 June 2022

Issue date: June 2022

Copyright

Acknowledgements

We thank the Bioinformatics Center and School of Life Science of the University of Science and Technology of China, School of Life Science, for providing supercomputing resources for this project. We thank the organizers of the BCI Controlled Robot Contest in World Robot Contest for their support.

Rights and permissions

This article is published with open access at journals.sagepub.com/home/BSA

Creative Commons Non Commercial CC BY- NC: This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (http://www.creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/ en-us/nam/open-access-at-sage).