Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Geometric Neural Network based on Phase Space for BCI-EEG decoding (2403.05645v3)

Published 8 Mar 2024 in eess.SP, cs.AI, cs.LG, and q-bio.NC

Abstract: Objective: The integration of Deep Learning (DL) algorithms on brain signal analysis is still in its nascent stages compared to their success in fields like Computer Vision. This is particularly true for BCI, where the brain activity is decoded to control external devices without requiring muscle control. Electroencephalography (EEG) is a widely adopted choice for designing BCI systems due to its non-invasive and cost-effective nature and excellent temporal resolution. Still, it comes at the expense of limited training data, poor signal-to-noise, and a large variability across and within-subject recordings. Finally, setting up a BCI system with many electrodes takes a long time, hindering the widespread adoption of reliable DL architectures in BCIs outside research laboratories. To improve adoption, we need to improve user comfort using, for instance, reliable algorithms that operate with few electrodes. Approach: Our research aims to develop a DL algorithm that delivers effective results with a limited number of electrodes. Taking advantage of the Augmented Covariance Method and the framework of SPDNet, we propose the Phase-SPDNet architecture and analyze its performance and the interpretability of the results. The evaluation is conducted on 5-fold cross-validation, using only three electrodes positioned above the Motor Cortex. The methodology was tested on nearly 100 subjects from several open-source datasets using the Mother Of All BCI Benchmark (MOABB) framework. Main results: The results of our Phase-SPDNet demonstrate that the augmented approach combined with the SPDNet significantly outperforms all the current state-of-the-art DL architecture in MI decoding. Significance: This new architecture is explainable and with a low number of trainable parameters.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. Brain–computer interfaces in neurological rehabilitation. The Lancet Neurology, 7(11):1032–1043, 2008.
  2. Combining brain–computer interface and virtual reality for rehabilitation in neurological diseases: A narrative review. Annals of physical and rehabilitation medicine, 64(1):101404, 2021.
  3. A generic noninvasive neuromotor interface for human-computer interaction. bioRxiv, pages 2024–02, 2024.
  4. The benefits and challenges of chatgpt: An overview. Frontiers in Computing and Intelligent Systems, 2(2):81–83, 2022.
  5. Highly accurate protein structure prediction with alphafold. Nature, 596(7873):583–589, 2021.
  6. Deep learning-based electroencephalography analysis: a systematic review. Journal of neural engineering, 16(5):051001, 2019.
  7. Classification of BCI-EEG based on augmented covariance matrix. arXiv preprint arXiv:2302.04508, 2023.
  8. A riemannian network for spd matrix learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017a.
  9. Functional Connectivity Ensemble Method to Enhance BCI Performance (FUCONE). IEEE Transactions on Biomedical Engineering, 69(9):2826–2838, 2022. doi: 10.1109/TBME.2022.3154885.
  10. Mother of all bci benchmarks v1.0. doi.org/10.5281/zenodo.10034223, 2023. DOI: 10.5281/zenodo.10034223.
  11. Alexander J Casson. Wearable EEG and beyond. Biomedical engineering letters, 9(1):53–71, 2019.
  12. Encoding and Decoding Framework to Uncover the Algorithms of Cognition. In The Cognitive Neurosciences. The MIT Press, 05 2020. ISBN 9780262356176.
  13. MOABB: trustworthy algorithm benchmarking for BCIs. Journal of neural engineering, 15(6):066011, 2018.
  14. Deep learning with convolutional neural networks for EEG decoding and visualization. Human Brain Mapping, aug 2017a. ISSN 1097-0193. doi: 10.1002/hbm.23730.
  15. Data augmentation for learning predictive models on EEG: a systematic comparison. Journal of Neural Engineering, 19(6):066020, 11 2022a. doi: 10.1088/1741-2552/aca220.
  16. Machine learning of brain-specific biomarkers from EEG. bioRxiv, pages 2023–12, 2023. doi: 10.1101/2023.12.15.571864.
  17. Brain decoding: toward real-time reconstruction of visual perception. In The Twelfth International Conference on Learning Representations, 2024.
  18. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. Journal of neural engineering, 15(5):056013, 2018.
  19. EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery brain–machine interfaces. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 2958–2965. IEEE, 2020.
  20. EEG-ITNet: An explainable inception temporal convolutional network for motor imagery classification. IEEE Access, 10:36672–36685, 2022.
  21. Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeX. arXiv preprint arXiv:2207.12369, 2022.
  22. A Riemannian Network for SPD Matrix Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1), Feb. 2017b.
  23. Riemannian Embedding Banks for Common Spatial Patterns with EEG-based SPD Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1):854–862, May 2021.
  24. MAtt: A Manifold Attention Network for EEG Decoding. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho, editors, Advances in Neural Information Processing Systems, 2022.
  25. SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG. Advances in Neural Information Processing Systems, 35:6219–6235, 2022.
  26. DreamNet: A Deep Riemannian Manifold Network for SPD Matrix Learning. In Proceedings of the Asian Conference on Computer Vision (ACCV), pages 3241–3257, December 2022.
  27. Ce Ju and Cuntai Guan. Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification. IEEE Transactions on Neural Networks and Learning Systems, 34:10955–10969, 2022.
  28. A discriminative SPD feature learning approach on Riemannian manifolds for EEG classification. Pattern Recognition, 143:109751, 2023. ISSN 0031-3203.
  29. LGL-BCI: A Lightweight Geometric Learning Framework for Motor Imagery-Based Brain-Computer Interfaces. ArXiv, abs/2310.08051, 2023.
  30. Ce Ju and Cuntai Guan. Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective From the Time–Frequency Analysis. IEEE Transactions on Neural Networks and Learning Systems, pages 1–15, 2023. doi: 10.1109/TNNLS.2023.3307470.
  31. U-SPDNet: An SPD manifold learning-based neural network for visual classification. Neural Networks, 161:382–396, 2023. ISSN 0893-6080.
  32. Reducing the Dimensionality of SPD Matrices with Neural Networks in BCI. Mathematics, 11(7), 2023. ISSN 2227-7390.
  33. Functional connectivity learning via Siamese-based SPD matrix representation of brain imaging data. Neural Networks, 163:272–285, 2023. ISSN 0893-6080. doi: 10.1016/j.neunet.2023.04.004.
  34. Deep Riemannian Networks for EEG Decoding. ArXiv, abs/2212.10426, 2022.
  35. Federated Transfer Learning for EEG Signal Classification. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pages 3040–3045, 2020. doi: 10.1109/EMBC44109.2020.9175344.
  36. Riemannian batch normalization for SPD neural networks. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  37. SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space. arXiv preprint arXiv:2312.08200, 2023.
  38. Diffusion Models for Constrained Domains. arXiv preprint arXiv:2304.05364, 2023.
  39. How Sensitive Are EEG Results to Preprocessing Methods: A Benchmarking Study. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(5):1081–1090, 2020. doi: 10.1109/TNSRE.2020.2980223.
  40. MEG and EEG data analysis with MNE-Python. Frontiers in Neuroscience, 7:267, 2013. ISSN 1662-453X. doi: 10.3389/fnins.2013.00267.
  41. Autoreject: Automated artifact rejection for MEG and EEG data. NeuroImage, 159:417–429, 2016.
  42. Faster ICA under orthogonal constraint. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4464–4468. IEEE, 2018.
  43. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. Journal of neural engineering, 15(3):031005, 2018.
  44. CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals. In International Conference on Learning Representations, 2022b.
  45. High-dimensional phase space reconstruction with a convolutional neural network for structural health monitoring. Sensors, 21(10):3514, 2021.
  46. Multivariate phase space reconstruction and Riemannian manifold for sleep stage classification. Biomedical Signal Processing and Control, 88:105572, 2024. ISSN 1746-8094. doi: 10.1016/j.bspc.2023.105572.
  47. Floris Takens. Detecting strange attractors in turbulence. In Dynamical systems and turbulence, Warwick 1980, pages 366–381. Springer, 1981.
  48. Florias Takens. Detecting Nonlinearities In Stationary Time Series. International Journal of Bifurcation and Chaos, 03(02):241–256, 1993. doi: 10.1142/S0218127493000192.
  49. Lyle Noakes. The takens embedding theorem. International Journal of Bifurcation and Chaos, 01(04):867–872, 1991.
  50. Geometry from a time series. Physical review letters, 45(9):712, 1980.
  51. Selecting embedding delays: An overview of embedding techniques and a new method using persistent homology. Chaos: An Interdisciplinary Journal of Nonlinear Science, 33(3):032101, 03 2023. ISSN 1054-1500. doi: 10.1063/5.0137223.
  52. Chetan Nichkawde. Optimal state-space reconstruction using derivatives on projected manifold. Physical Review E, 87(2):022905, 2013.
  53. Diffusion tensor imaging: concepts and applications. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, 13(4):534–546, 2001.
  54. Visualization and processing of tensor fields. Springer Science & Business Media, 2005.
  55. Riemannian geometry applied to bci classification. In International conference on latent variable analysis and signal separation, pages 629–636. Springer, 2010.
  56. A metric for covariance matrices. Geodesy-the Challenge of the 3rd Millennium, pages 299–309, 2003.
  57. Maher Moakher. A differential geometric approach to the geometric mean of symmetric positive-definite matrices. SIAM journal on matrix analysis and applications, 26(3):735–747, 2005.
  58. Geometric means in a novel vector space structure on symmetric positive-definite matrices. SIAM journal on matrix analysis and applications, 29(1):328–347, 2007.
  59. pyRiemann/pyRiemann: v0.5. doi.org/10.5281/zenodo.7547583, 2023. DOI: 10.5281/zenodo.7547583.
  60. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  61. Riemannian adaptive optimization methods. arXiv preprint arXiv:1810.00760, 2018.
  62. Geoopt: Riemannian optimization in pytorch. arXiv preprint arXiv:2005.02819, 2020.
  63. Review of the BCI competition IV. Frontiers in neuroscience, page 55, 2012.
  64. Brain–computer communication: motivation, aim, and impact of exploring a virtual apartment. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 15(4):473–482, 2007.
  65. EEG datasets for motor imagery brain–computer interface. GigaScience, 6(7):gix034, 2017.
  66. Deep learning with convolutional neural networks for EEG decoding and visualization. Human brain mapping, 38(11):5391–5420, 2017b.
  67. Evaluation of EEG oscillatory patterns and cognitive process during simple and compound limb motor imagery. PloS one, 9(12):e114853, 2014.
  68. A fully automated trial selection method for optimization of motor imagery based brain-computer interface. PloS one, 11(9):e0162657, 2016.
  69. Marc Jeannerod. Mental imagery in the motor context. Neuropsychologia, 33(11):1419–1432, 1995.
  70. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In 2018 IEEE winter conference on applications of computer vision (WACV), pages 839–847. IEEE, 2018.
  71. An empirical comparison of deep learning explainability approaches for EEG using simulated ground truth. Scientific Reports, 13(1):17709, 2023.
  72. Aligning artificial intelligence with climate change mitigation. Nature Climate Change, 12(6):518–527, 2022.
  73. mlco2/codecarbon: v2.2.7, July 2023. DOI: 10.5281/zenodo.8181237.
  74. Learning from other subjects helps reducing brain-computer interface calibration time. In 2010 IEEE International conference on acoustics, speech and signal processing, pages 614–617. IEEE, 2010.
  75. Riemannian approaches in brain-computer interfaces: a review. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(10):1753–1762, 2016.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets