Journal of Radio Electronics. eISSN 1684-1719. 2025. ¹1

Contents

Full text in Russian (pdf)

Russian page

 

 

DOI: https://doi.org/10.30898/1684-1719.2025.1.1  

 

 

 

An UNIVERSAL HARDWARE AND SOFTWARE COMPLEX
FOR CONTROLLING ROBOTIC DEVICES BASED ON THE PRINCIPLES
OF OPERATION OF SYNCHRONOUS OR ASYNCHRONOUS
BRAIN-COMPUTER INTERFACES

 

D.V. Zhuravlev1, A.N. Golubinsky2, A.A. Reznichenko1

 

1Voronezh State Technical University
394006, Russia, Voronezh, 20th Anniversary of October str., 84

2A.A. Harkevich Institute of Information Transmission Problems, RAS
127051, Russia, Moscow, Bolshoy Karetny Lane, 19, building 1

 

The paper was received November 8, 2024.

 

Abstract. The article discusses the issues of research and development of the main modules of the software and hardware complex for controlling robotic devices using bioelectric signals of the brain. The aim of the work is to develop theoretical and practical foundations for the implementation of a universal hardware and software control complex for robotic devices based on brain-computer interfaces. The developed complex allows you to organize its work on the basis of both synchronous and asynchronous interface types. This shows the versatility of the complex. The article presents the main differences between asynchronous brain-computer interfaces and synchronous ones. In order to ensure the correct operation of the classifier, data preprocessing techniques were developed and tested for both cases, both for the use of synchronous and asynchronous brain-computer interfaces. A unified data classifier architecture based on the multilayer perceptron model has been developed, suitable for both the classification of P300 waves (using synchronous interfaces) and imaginary movements (using asynchronous interfaces). A system has been tested that implements the uses of synchronous brain-computer interface online. The average accuracy of P300 wave recognition was 60% with cyclic repetition of visual stimuli in continuous operation of the system. A system was also tested that implements the use of an asynchronous brain-computer interface based on the classification of motor images (imaginary movements of the left and right hands). The average online classification accuracy was 65%. The effectiveness and relevance of asynchronous brain-computer interfaces has been confirmed by the ability to generate control signals to a robotic device using mental imaginary movements of the operator with an average accuracy of at least 65%. Moreover, the system has shown operability with any operator without prior training. This shows the expediency of developing the technology of non-invasive brain-computer interfaces.

Keywords: Brain-computer interface, wave P300, synchronous interface, asynchronous interface, classification, motor images, hardware and software complex.

Financing: The research was carried out at the expense of a grant from the Russian Science Foundation No. 24-29-20168, https://rscf.ru/project/24-29-20168/

Correspondingauthor: Zhuravlev Dmitry Vladimirovich, ddom1@yandex.ru

 

References

1. Zhuravlev D.V. Apparatura dlya ehlektroehntsefalograficheskikh issledovanii. – 2021.

2. Schwartz A.B. Cortical neural prosthetics // Annu. Rev. Neurosci. – 2004. – Ò. 27. – ¹. 1. – Ñ. 487-507.

3. Homer M.L. et al. Sensors and decoding for intracortical brain computer interfaces // Annual review of biomedical engineering. – 2013. – Ò. 15. – ¹. 1. – Ñ. 383-405.

4. Stankevich L.A. i dr. Klassifikatsiya ehlektroehntsefalograficheskikh patternov voobrazhaemykh dvizhenii pal'tsami ruki dlya razrabotki interfeisa mozg-komp'yuter // Informatika i avtomatizatsiya. – 2015. – T. 3. – ¹. 40. – S. 163-182.

5. Mayorov O.Y., Fenchenko V.N. Multifractal analysis in the study of brain bioelectric activity // Zn. Kibernetika i vychislitel’naya tekhnika. – Ñ. 81-94.

6. Ganin I.P., Kaplan A.YA. Izuchenie ehffektov variativnosti potentsialov mozga cheloveka v interfeise mozG–komp'yuter na volne P300 // Vestnik Rossiiskogo gosudarstvennogo meditsinskogo universiteta. – 2022. – ¹. 3. – S. 78-85.

7. Syskov A.M., Borisov V.I., Petrenko T.S. Proektirovanie mul'timodal'nykh interfeisov mozg-komp'yuter: uchebno-metodicheskoe posobie. – 2023.

8. Wetzel D. et al. Significance of EEG-electrode combinations while calculating filters with common spatial patterns // GMS German Medical Science. – 2024. – Ò. 22. – Ñ. Doc08.

9. Chakole A.R. et al. Review of EEG signal classification // Information and Communication Technology for Intelligent Systems: Proceedings of ICTIS 2018, Volume 2. – Springer Singapore, 2019. – Ñ. 105-114.

10. Lovgonyuk V.N., Nuss EH.A. Modeli i metody apparatnoi realizatsii iskusstvennykh neironnykh setei // Science and technology innovations-2023. – 2023. – S. 100-109.

11. Kondur A.A. i dr. Vosstanovlenie dvigatel'noi funktsii ruki posle insul'ta s pomoshch'yu interfeisa “mozg-komp'yuteR”, upravlyayushchego ehkzoskeletom kisti: ehffekt povtornykh gospitalizatsii // Fiziologiya cheloveka. – 2020. – T. 46. – ¹. 3. – S. 99-110.

12. Gordleeva S.Y. et al. Exoskeleton control system based on motor-imaginary brain–computer interface // Sovremennye tekhnologii v meditsine. – 2017. – T. 9. – ¹. 3 (eng). – S. 31-36.

13. Zhuravlev D.V., Reznichenko A.A. Interfeis mozg-komp'yuter na volne P300 s ispol'zovaniem neironnykh setei // Radioehlektronnaya tekhnika. – 2022. – S. 142-151.

14. Roman-Gonzalez A. EEG signal processing for BCI applications // Human–computer systems interaction: backgrounds and applications. – 2012. – Ò. 2. – Ñ. 571-591.

15. Zhang W. et al. A review of EEG-based brain-computer interface systems design // Brain Science Advances. – 2018. – Ò. 4. – ¹. 2. – Ñ. 156-167.

16. Golubinskii A.N., Tolstykh A.A. O primenenii svertochnykh neironnykh setei dlya klassifikatsii motoriki na osnove signalov EHEHG interfeisa mozg-komp'yuter // Naukosfera. – 2021. – ¹. 2-1. – S. 85-88.

For citation:

Zhuravlev D.V., Golubinsky A.N., Reznichenko A.A. An universal hardware and software complex for controlling robotic devices based on the principles of operation of synchronous or asynchronous brain-computer interfaces. // Journal of Radio Electronics. – 2025. – ¹. 1. https://doi.org/10.30898/1684-1719.2025.1.1 (In Russian)