Abstract
Brain-Machine Interface (BMI) is a control paradigm involving using brain signal to generate control commands for other devices. A non-invasive method of brain signal recording such as Electroencephalogram (EEG) is widely used. Modern approaches for BMI tend to utilize Deep Learning (DL) such as Convolutional Neural Network (CNN) to extract essential features as well as improve the classification accuracy. Nonetheless, EEG is a subject dependent signal wherein individuals exhibit a distinct signal pattern even when performing identical tasks. In addition, DL requires a huge amount of data which leads to longer training time. In this paper we propose transfer learning (TL) to improve the recognition rate and reduce the training time of BMI systems. We implement multiple conditions to evaluate the TL performance. The experiments using competition IV b2 dataset mental imaginary tasks and the dataset collected in our lab for several grasping hand motions are utilized to evaluate the TL performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bamdad, M., Zarshenas, H., Auais, M.A.: Application of BCI systems in neurorehabilitation: a scoping review. Disabil. Rehabil. Assist. Technol. 10, 355–364 (2015)
Aghazadeh, R., Montagna, F., Benatti, S., Rossi, D., Frounchi, J.: Compressed sensing based seizure detection for an ultra low power multi-core architecture. In: 2018 International Conference on High Performance Computing & Simulation (HPCS) (2018)
Vézard, L., Legrand, P., Chavent, M., Faïta-Aïnseba, F., Trujillo, L.: EEG classification for the detection of mental states. Appl. Soft Comput. 32, 113–131 (2015)
Gannouni, S., Aledaily, A., Belwafi, K., Aboalsamh, H.: Emotion detection using electroencephalography signals and a zero-time windowing-based epoch estimation and relevant electrode identification. Sci. Rep. 11 (2021)
Bhattacharyya, S., Khasnobish, A., Chatterjee, S., Konar, A., Tibarewala, D.N.: Performance Analysis of LDA, QDA and KNN algorithms in left-right limb movement classification from EEG Data. In: 2010 International Conference on Systems in Medicine and Biology (2010)
Ines, H., Slim, Y., Noureddine, E.: EEG classification using support vector machine. In: 10th International Multi-Conferences on Systems, Signals & Devices 2013 (SSD13) (2013)
Wang, J., Yu, G., Zhong, L., Chen, W., Sun, Y.: Classification of EEG signal using convolutional neural networks. In: 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA) (2019)
Xu, G., et al.: A deep transfer convolutional neural network framework for EEG signal classification. IEEE Access 7, 112767–112776 (2019)
Li, M.-A., Xu, D.-Q.: A transfer learning method based on VGG-16 convolutional neural network for MI classification. In: 2021 33rd Chinese Control and Decision Conference (CCDC) (2021)
Kim, D., Woo, Y., Jeong, J., Kim, D.-K., Lee, J.-G.: Sleep stage classification for inter-institutional transfer learning. In: 2021 International Conference on Information and Communication Technology Convergence (ICTC) (2021)
BCI Competition IV Homepage. https://www.bbci.de/competition/iv. Accessed 12 Dec 2021
Pongthanisorn, G., Shirai, A., Sugiyama, S., Capi, G.: Combination of reinforcement and deep learning for EEG channel optimization on brain-machine interface systems. In: 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (2023)
Leeb, R., Lee, F., Keinrath, C., Scherer, R., Bischof, H., Pfurtscheller, G.: Brain-computer communication: MOTIVATION, AIM, and impact of exploring a virtual apartment. IEEE Trans. Neural Syst. Rehabil. Eng. 15, 473–482 (2007)
BNCI Horizon 2020. http://bnci-horizon-2020.eu/database/data-sets. Accessed 30 Jan 2023
Chen, Z., Wang, Y., Song, Z.: Classification of motor imagery electroencephalography signals based on image processing method. Sensors 21, 4646 (2021)
Chaudhary, S., Taran, S., Bajaj, V., Sengur, A.: Convolutional neural network based approach towards motor imagery tasks EEG signals classification. IEEE Sens. J. 19, 4494–4500 (2019)
Lee, H.K., Choi, Y.-S.: Application of continuous wavelet transform and convolutional neural network in decoding motor imagery brain-computer interface. Entropy 21, 1199 (2019)
Lawhern, V.J., Solon, A.J., Waytowich, N.R., Gordon, S.M., Hung, C.P., Lance, B.J.: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J. Neural Eng. 15, 056013 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017)
Abo-Zahhad, M., Ahmed, S.M., Abbas, S.N.: A new EEG acquisition protocol for biometric identification using eye blinking signals. Int. J. Intell. Syst. Appl. 7, 48–54 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pogthanisorn, G., Takahashi, R., Capi, G. (2023). Learning Time and Recognition Rate Improvement of CNNs Through Transfer Learning for BMI Systems. In: Meder, F., Hunt, A., Margheri, L., Mura, A., Mazzolai, B. (eds) Biomimetic and Biohybrid Systems. Living Machines 2023. Lecture Notes in Computer Science(), vol 14157. Springer, Cham. https://doi.org/10.1007/978-3-031-38857-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-38857-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38856-9
Online ISBN: 978-3-031-38857-6
eBook Packages: Computer ScienceComputer Science (R0)