Abstract
Motor imagery (MI) electroencephalogram (EEG) recognition is currently widely used in brain-computer interface (BCI) devices for people with motor disabilities to achieve various motor interaction functions with the outside world. Over 70% of recent researches use convolutional neural networks (CNN) for recognition of MI. However, using CNN is often difficult to fully utilize the temporal features of long time series in EEG. It may lead to part of the difference information among subjects not being learned by the CNN. In this paper, we introduce a multi-branch CNN that integrates a gate recurrent unit (GRU) module. In this model, the serial module extracts rough features in the temporal and spatial domains, and the parallel module uses different scale convolution blocks and GRU modules to extract time series information in different ranges to improve the precision of learning. This training strategy not only retains the advantages of CNN in extracting temporal and spatial features, but also makes full use of the long time series information extracted by GRU so as to improve the classification accuracy. Experimental results show that our proposed framework has higher performance compared to other typical models, such as DeepNet, EEGNet. The within-subject average classification accuracy reaches 74.4% on BCI competition IV-2a dataset, and the minimum accuracy among subjects increases by 5.6%. This indicates that the proposed model has good generalization ability among different subjects, thus promoting the implementation of personalized real-time BCI devices in the future.
This work is supported by the National Natural Science Foundation of China under Grant No. 62072468.
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
Similar content being viewed by others
References
Al-Saegh, A., Dawwd, S.A., Abdul-Jabbar, J.M.: Deep learning for motor imagery EEG-based classification: a review. Biomed. Signal Process. Control 63, 102172 (2021)
Altaheri, H., et al.: Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review. Neural Comput. Appl. 35, 1–42 (2021)
Ang, K.K., Guan, C.: EEG-based strategies to detect motor imagery for control and rehabilitation. IEEE Trans. Neural Syst. Rehabil. Eng. 25(4), 392–401 (2016)
Bai, Z., Yang, R., Liang, Y.: Mental task classification using electroencephalogram signal. arXiv preprint arXiv:1910.03023 (2019)
Dai, G., Zhou, J., Huang, J., Wang, N.: HS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification. J. Neural Eng. 17(1), 016025 (2020)
Garcia-Moreno, F.M., Bermudez-Edo, M., Rodríguez-Fórtiz, M.J., Garrido, J.L.: A CNN-LSTM deep learning classifier for motor imagery EEG detection using a low-invasive and low-cost BCI headband. In: 2020 16th International Conference on Intelligent Environments (IE), pp. 84–91. IEEE (2020)
Jin, X., et al.: CTNN: a convolutional tensor-train neural network for multi-task brainprint recognition. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 103–112 (2020)
Li, G., et al.: An EEG data processing approach for emotion recognition. IEEE Sens. J. 22(11), 10751–10763 (2022)
Li, X., et al.: EEG motor imagery classification based on multi-spatial convolutional neural network. In: 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD), pp. 433–437. IEEE (2022)
Li, Y., Zhang, X.R., Zhang, B., Lei, M.Y., Cui, W.G., Guo, Y.Z.: A channel-projection mixed-scale convolutional neural network for motor imagery EEG decoding. IEEE Trans. Neural Syst. Rehabil. Eng. 27(6), 1170–1180 (2019)
Lin, P.J., et al.: CNN-based prognosis of BCI rehabilitation using EEG from first session BCI training. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 1936–1943 (2021)
Mai, N.D., Long, N.M.H., Chung, W.Y.: 1D-CNN-based BCI system for detecting emotional states using a wireless and wearable 8-channel custom-designed EEG headset. In: 2021 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS), pp. 1–4. IEEE (2021)
Mattioli, F., Porcaro, C., Baldassarre, G.: A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface. J. Neural Eng. 18(6), 066053 (2022)
Musallam, Y.K., et al.: Electroencephalography-based motor imagery classification using temporal convolutional network fusion. Biomed. Signal Process. Control 69, 102826 (2021)
Pathan, S.M.K., Rana, M.M.: Investigation on classification of motor imagery signal using bidirectional LSTM with effect of dropout layers. In: 2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE), pp. 1–5. IEEE (2022)
Petoku, E., Capi, G.: Object movement motor imagery for EEG based BCI system using convolutional neural networks. In: 2021 9th International Winter Conference on Brain-Computer Interface (BCI), pp. 1–5. IEEE (2021)
Schirrmeister, R.T., et al.: Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 38(11), 5391–5420 (2017)
Wu, H., et al.: A parallel multiscale filter bank convolutional neural networks for motor imagery EEG classification. Front. Neurosci. 13, 1275 (2019)
Yang, Y., Wu, Q., Qiu, M., Wang, Y., Chen, X.: Emotion recognition from multi-channel EEG through parallel convolutional recurrent neural network. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2018)
Zhang, D., Yao, L., Chen, K., Wang, S., Chang, X., Liu, Y.: Making sense of spatio-temporal preserving representations for EEG-based human intention recognition. IEEE Trans. Cybern. 50(7), 3033–3044 (2019)
Zhang, H.Y., Stevenson, C.E., Jung, T.P., Ko, L.W.: Stress-induced effects in resting EEG spectra predict the performance of SSVEP-based BCI. IEEE Trans. Neural Syst. Rehabil. Eng. 28(8), 1771–1780 (2020)
Zhang, R., Zong, Q., Dou, L., Zhao, X.: A novel hybrid deep learning scheme for four-class motor imagery classification. J. Neural Eng. 16(6), 066004 (2019)
Zhang, Z., et al.: A novel deep learning approach with data augmentation to classify motor imagery signals. IEEE Access 7, 15945–15954 (2019)
Zhao, X., Zhang, H., Zhu, G., You, F., Kuang, S., Sun, L.: A multi-branch 3D convolutional neural network for EEG-based motor imagery classification. IEEE Trans. Neural Syst. Rehabil. Eng. 27(10), 2164–2177 (2019)
Zhao, X., et al.: Deep CNN model based on serial-parallel structure optimization for four-class motor imagery EEG classification. Biomed. Signal Process. Control 72, 103338 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, J., Guo, W., Yu, H., Wang, Y. (2024). Motor Imagery EEG Recognition Based on an Improved Convolutional Neural Network with Parallel Gate Recurrent Unit. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14432. Springer, Singapore. https://doi.org/10.1007/978-981-99-8543-2_26
Download citation
DOI: https://doi.org/10.1007/978-981-99-8543-2_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8542-5
Online ISBN: 978-981-99-8543-2
eBook Packages: Computer ScienceComputer Science (R0)