Review of solutions for the application of example of machine learning methods for Motor Imagery in correlation with Brain-Computer Interfaces

• Autorzy: Paszkiel Szczepan , Rojek Ryszard , Lei Ningrong , Castro Maria Antonio

Identyfikatory

DOI

10.15199/48.2021.11.20

Warianty tytułu

PL

Przegląd rozwiązań do zastosowania metod uczenia maszynowego na potrzeby obrazowania motorycznego w korelacji z interfejsami mózg-komputer

• Języki publikacji: EN

Abstrakty

EN

Presently, numerous public databases presenting the collected EEG signals, including the ones in the scope of Motor Imagery (MI), are available. Simultaneously, machine-learning methods, which enable effective and fast discovering of information, also in the sets of biomedical data, are constantly being developed. In this paper, a set of 30 of some of the latest scientific publications from the years 2016-2021 has been analyzed. The analysis covered, among others: public data repositories in the form of EEG signals as input data; numbers and types of the analyzed tasks in the scope of MI in the above-mentioned databases; and Deep Learning (DL) architectures.

PL

Obecnie dostępne są liczne ogólnodostępne bazy danych prezentujące zebrane sygnały EEG, w tym z zakresu obrazowania motorycznego (MI). Jednocześnie stale rozwijane są metody uczenia maszynowego, które umożliwiają efektywne i szybkie odkrywanie informacji, także w zbiorach danych biomedycznych. W niniejszym artyule przeanalizowano zestaw 30 spośród najnowszych publikacji naukowych z lat 2016- 2021. Analizie poddano m.in.: publiczne repozytoria danych w postaci sygnałów EEG jako dane wejściowe; liczby i rodzaje analizowanych zadań z zakresu obrazowania motorycznego w ww. bazach; i architektury Deep Learning (DL).

Słowa kluczowe

EN

motor imagery; EEG; BCI; machine learning; deep learning; deep neural network

PL

obrazowanie motoryczne; EEG; BCI; uczenie maszynowe; głębokie uczenie; głębokie sieci neuronowe

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2021
• Tom: R. 97, nr 11
• Strony: 111--116
• Opis fizyczny: Bibliogr. 37 poz., rys., tab.

Twórcy

autor

Paszkiel Szczepan

• Politechnika Opolska, Instytut Elektroenergetyki i Energii Odnawialnej, ul. Prószkowska 76, 45-271 Opole

• https://orcid.org/0000-0002-4917-5712

autor

Rojek Ryszard

• Politechnika Opolska, Instytut Elektroenergetyki i Energii Odnawialnej, ul. Prószkowska 76, 45-271 Opole

autor

Lei Ningrong

• Sheffield Hallam University, City Campus, Howard Street, Sheffield, S1 1WB, UK

autor

Castro Maria Antonio

• Polytechnic of Leiria, Morro do Lena – Alto do Vieiro, Apartado 4137, 2411-901 Leiria, Portugal

Bibliografia

• 1. Paszkiel S., Sikora M.: The Use of Brain-Computer Interface to Control Unmanned Aerial Vehicle, Automation 2019: Progress In Automation, Robotics And Measurement Techniques, Edited by: Szewczyk, R; Zielinski, C; Kaliczynska, M, Book Series: Advances in Intelligent Systems and Computing, Volume: 920, (2020), pp. 583-598
• 2. Paszkiel S., Control based on brain-computer interface technology for video-gaming with virtual reality techniques, Journal of Automation, Mobile Robotics & Intelligent Systems, (2016), VOLUME 10, N° 4, DOI: 10.14313/JAMRIS_4-2016/26, pp. 3-7
• 3. Al-Qaysi Z.T., Zaidan B.B., Zaidan A. A. et al., Review of the EEG-based wheelchair control system: Consistent taxonomy, open challenges and recommendations, Comput. Methods Biomed Programs. 164 (2018) pp. 221–237
• 4. Sitaram R., Zhang H., Guan C. et al., Time classification of multichannel near-infrared spectroscopy signals for motor images for brain-computer interface development, Neuroimage 34 (4) (2007) pp. 1416–1427
• 5. Vourvopoulos A., Badia S.B.I, Liarokapis F., EEG correlates of video game experience and user profile in motor-imagerybased brain – computer interaction, Vis. Comput. 33 (4) (2017) pp. 533-546
• 6. Wang Z., Yu Y., Xu M., et al., Towards a hybrid BCI gaming paradigm based on Motor Imagery and SSVEP, Int. Journal Hum. – Comput. Interact. 35 (3) (2019) pp. 97-205
• 7. Zhu X. et al., Separated channel convolutional neural network to realize the training free Motor Imagery BCI systems Biomedical Signal Processing 49 (2019); pp. 396–403
• 8. Wu H. et al. A parallel multiscale filter bank convolutional neural networks for Motor Imagery EEG classification, Frontiers Neurosciences 13 (2019); pp. 1–9
• 9. Li Y. et al. A channel-projection mixed-scale convolutional neural network for Motor Imagery EEG decoding, Transactions on Neural Systems and Rehabilitation Engineering 27 (2019); pp. 1170–1180
• 10. Tayeb Z. et al., Validating deep neural networks for online decoding of Motor Imagery movements from eeg signals, Sensors MDPI, 19 (1) (2019)
• 11. Zhang D. et al., Making sense of spatio-temporal preserving representations for EEG-Based human intention recognition, Transactions on Cybernetics (2019); pp. 1–12
• 12. Li F. et al., A novel simplified convolutional neural network classification algorithm of Motor Imagery EEG signals based on DL, Applied Sciences MDPI, 10 (2020) 1605
• 13. Tang X. et al., Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network, Artificial Intelligence in Medicine 101 (2019); 101747
• 14. Dai G. et al., HS-CNN: a CNN with hybrid convolution scale for EEG Motor Imagery classification, Journal of Neural Engineering 17 (1) (2020)
• 15. Olivas-Padilla B.E. et al., Classification of multiple Motor Imagery using deep convolutional neural networks and spatial filters, Applied Soft Computuing Journal 75 (2019); pp. 461–472
• 16. Xu G. et al., A deep transfer convolutional neural network framework for EEG signal classification, Access 7 (2019) 112767–112776, https://doi.org/ 10.1109/access.2019.2930958
• 17. Li D. et al., Densely feature fusion based on convolutional neural networks for Motor Imagery EEG classification, Access 7 (2019); pp. 132720–132730
• 18. Amin S.U. et al., Multilevel weighted feature fusion using convolutional neural networks for EEG Motor Imagery classification, Connected Health in Smart Cities, 2020, pp. 233–254
• 19. Tabar Y.R., A novel DL approach for classification of EEG Motor Imagery signals, Journal Neural Engineering 14 (1) (2016) 16003
• 20. Schirrmeister R.T., DL with convolutional neural networks for EEG decoding and visualization, Wiley, UK, (2017)
• 21. Zhang R. et al., A novel hybrid DL scheme for four-class Motor Imagery classification, Signal Processing in Medicine and Biology Symposium, SPMB (2017); pp. 1–7
• 22. Dai M., EEG classification of Motor Imagery using a novel DL framework, Sensors MDPI 19 (3) (2019) 1–16
• 23. Majidov I. et al., Efficient classification of Motor Imagery electroencephalography signals using DL methods, Sensors MDPI 19 (2019); pp. 1–13
• 24. Xu B. et al., Wavelet transform time-frequency image and convolutional network-based Motor Imagery EEG classification, Access 7 (2019); pp. 6084–6093
• 25. Ha K.W. et al., Motor imagery EEG classification using capsule networks, Sensors MDPI 19 (13) (2019) 2854
• 26. Hassanpour A. et al., A novel end-to-end DL scheme for classifying multi-class Motor Imagery electroencephalography signals, Expert Systems (2019); pp. 1–21
• 27. Tang X. et al., Semisupervised deep stacking network with adaptive learning rate strategy for Motor Imagery eeg recognition, Neural Computing 31 (2019); pp. 919–942
• 28. Wang P. et al., LSTM-based EEG classification in Motor Imagery tasks, Transactions on Neural Systems and Rehabilitation Engineering 26 (11) (2018) pp. 2086–2095
• 29. Lu N. et al., A DL scheme for Motor Imagery classification based on restricted boltzmann machines, Trans. Neural Syst. Rehabil. Eng. 25 (2017); pp. 566–576, https://doi.org/10.1109/ TNSRE.2016.2601240
• 30. Zhang K. et al., Adaptive transfer learning for EEG Motor Imagery classification with deep Convolutional Neural Network, Neural Networks (2021); 136, pp. 1-10
• 31. Zhang R. et al., Hybrid deep neural network using transfer learning for EEG Motor Imagery decoding, Biomedical Signal Processing and Control, Volume 63, (2021); pp. 102-144
• 32. She Q. et al., A hierarchical semi-supervised extreme learning machine method for EEG recognition, Medicine Biolology Engineering Computing 57 (2019); pp. 147–157
• 33. Luo T. et al., Exploring spatial-frequency-sequential relationships for Motor Imagery classification with recurrent neural network, BMC Bioinformatics 19 (2018); pp. 1–18
• 34. Chaudhary S., et al., Convolutional neural network based approach towards Motor Imagery tasks EEG signals classification, Sensors Journal 19 (2019); pp. 4494–4500
• 35. Lawhern V., et al., EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces, Journal Neural Engineering 15 (2018); pp. 1–30
• 36. Taheri S., et al., Convolutional neural network based features for Motor Imagery EEG signals classification in braincomputer interface system, SN Applied Sciences MDPI 2 (2020)
• 37. Paszkiel S., Dobrakowski P., Brain-computer technology based training system in the field of Motor Imagery, IET Science Measurement and Technology, WILEY, London, UK (2020), pp. 1014–1018

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).