Abstract
Raw EEG signal is dynamically collected from electrode channels distributing on the scalp surface and stored in computers as a 2D array of electrode channel (space) and time. In the past, most experiments were based on pure 2D EEG signal array of space and time. Shallow FBCSP ConvNet [5] is one of the successful models in handling 2D EEG signal array, which comes from FBCSP algorithm [4], a widely used algorithm in EEG decoding. With an original cropping strategy, Shallow FBCSP ConvNet reaches a high accuracy in EEG signal classification. In this paper, we propose a new cropping strategy to generate 3D EEG signal array of space, time and cropped piece. With redesigning the existing 2D Shallow FBCSP ConvNet model to become a 3D model, we obtained a good experimental result.
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
Huang, C., et al.: Predicting Human Intention-Behavior Through EEG Signal Analysis Using Multi-Scale CNN. IEEE/ACM Trans. Comput. Biol. Bioinform. 18(5), 1722–1729 (2021)
Koolen, N.: Automated classification of neonatal sleep states using EEG. Clin. Neurophysiol. 1286, 1100–1108 (2017), ISSN: 1388-2457
Qing, C., Qiao, R., Xu, X., Cheng, Y.: Interpretable Emotor recognition using EEG signals. IEEE Access 7, 94160–94170 (2019). https://doi.org/10.1109/ACCESS.2019.2928691
Ang, K.K., Chin, Z.Y., Zhang, H., Guan, C.: Filter bank common spatial pattern (FBCSP) in brain-computer interface. In IEEE International Joint Conference on Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence), pp 2390–2397 (2008)
Schirrmeister, R.T., et al.: Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 38(11), 5391–5420. Epub 2017 Aug 7. PMID: 28782865; PMCID: PMC5655781 https://doi.org/10.1002/hbm.23730
Gratton, G.: Dealing with artifacts: the EOG contamination of the event-related brain potential. Behav. Res. Methods. Instrum. Comput. 30(1), 44–53 (1998)
Schirrmeister, R.T., et al.: Deep learning with convolutional neural networks for EEG decoding and visualization. arXiv:1703.05051v1 [cs.LG]
Lawhern, V.J., Solon, A.J., Waytowich, N.R., Gordon, S.M., Hung, C.P., Lance, B.J.: EEGNet: a compact convolutional network for EEGbased brain-computer interfaces. J. Neural Eng. (2016). https://doi.org/10.1088/1741-2552/aace8c
Acknowledgements
This work is partially supported by Humanity and Social Science Foundation of the Ministry of Education of China (21A13022003), Zhejiang Provincial Natural Science Fund (LY19F030010), Zhejiang Provincial Social Science Fund (20NDJC216YB), Zhejiang Provincial Educational Science Scheme 2021 (GH2021642) and National Natural Science Foundation of China Grant (No. 72071049), Ningbo public welfare science and technology plan Grant No. 2021S093.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Y., Zhang, H.L., Lu, Y., Xue, Y. (2022). EEG Signal Classification Using Shallow FBCSP ConvNet with a New Cropping Strategy. In: Mahmud, M., He, J., Vassanelli, S., van Zundert, A., Zhong, N. (eds) Brain Informatics. BI 2022. Lecture Notes in Computer Science(), vol 13406. Springer, Cham. https://doi.org/10.1007/978-3-031-15037-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-15037-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15036-4
Online ISBN: 978-3-031-15037-1
eBook Packages: Computer ScienceComputer Science (R0)