Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 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

MBrain: A Multi-channel Self-Supervised Learning Framework for Brain Signals (2306.13102v1)

Published 15 Jun 2023 in eess.SP, cs.AI, and cs.LG

Abstract: Brain signals are important quantitative data for understanding physiological activities and diseases of human brain. Most existing studies pay attention to supervised learning methods, which, however, require high-cost clinical labels. In addition, the huge difference in the clinical patterns of brain signals measured by invasive (e.g., SEEG) and non-invasive (e.g., EEG) methods leads to the lack of a unified method. To handle the above issues, we propose to study the self-supervised learning (SSL) framework for brain signals that can be applied to pre-train either SEEG or EEG data. Intuitively, brain signals, generated by the firing of neurons, are transmitted among different connecting structures in human brain. Inspired by this, we propose MBrain to learn implicit spatial and temporal correlations between different channels (i.e., contacts of the electrode, corresponding to different brain areas) as the cornerstone for uniformly modeling different types of brain signals. Specifically, we represent the spatial correlation by a graph structure, which is built with proposed multi-channel CPC. We theoretically prove that optimizing the goal of multi-channel CPC can lead to a better predictive representation and apply the instantaneou-time-shift prediction task based on it. Then we capture the temporal correlation by designing the delayed-time-shift prediction task. Finally, replace-discriminative-learning task is proposed to preserve the characteristics of each channel. Extensive experiments of seizure detection on both EEG and SEEG large-scale real-world datasets demonstrate that our model outperforms several state-of-the-art time series SSL and unsupervised models, and has the ability to be deployed to clinical practice.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. EEG signal analysis for diagnosing neurological disorders using discrete wavelet transform and intelligent techniques. Sensors 20, 9 (2020), 2505.
  2. The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances. Data mining and knowledge discovery 31, 3 (2017), 606–660.
  3. Uncovering the structure of clinical EEG signals with self-supervised learning. Journal of Neural Engineering 18, 4 (2021), 046020.
  4. Language models are few-shot learners. In NeurIPS. 1877–1901.
  5. BrainNet: Epileptic wave detection from SEEG with hierarchical graph diffusion learning. In KDD. 2741–2751.
  6. Accurate EEG-based emotion recognition on combined features using deep convolutional neural networks. IEEE Access 7 (2019), 44317–44328.
  7. A simple framework for contrastive learning of visual representations. In ICML. 1597–1607.
  8. Wei Chen and Ke Shi. 2021. Multi-scale attention convolutional neural network for time series classification. Neural Networks 136 (2021), 126–140.
  9. Xinlei Chen and Kaiming He. 2021. Exploring simple siamese representation learning. In CVPR. 15745–15753.
  10. Deep learning for electroencephalogram (EEG) classification tasks: A review. Journal of Neural Engineering 16, 3 (2019), 031001.
  11. Spontaneous travelling cortical waves gate perception in behaving primates. Nature 587, 7834 (2020), 432–436.
  12. ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery 34, 5 (2020), 1454–1495.
  13. Minirocket: A very fast (almost) deterministic transform for time series classification. In KDD. 248–257.
  14. BERT: Pre-training of deep bidirectional Transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).
  15. Unsupervised visual representation learning by context prediction. In ICCV. 1422–1430.
  16. Differential entropy feature for EEG-based emotion classification. In NER. 81–84.
  17. Time-series representation learning via temporal and contextual contrasting. In IJCAI. 2352–2359.
  18. Unsupervised scalable representation learning for multivariate time series. In NeurIPS.
  19. Clive WJ Granger. 1969. Investigating causal relations by econometric models and cross-spectral methods. Econometrica: journal of the Econometric Society (1969), 424–438.
  20. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780.
  21. Lina Elsherif Ismail and Waldemar Karwowski. 2020. Applications of EEG indices for the quantification of human cognitive performance: A systematic review and bibliometric analysis. PloS one 15, 12 (2020), e0242857.
  22. Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR.
  23. Cognitive analysis of working memory load from eeg, by a deep recurrent neural network. In ICASSP. 2576–2580.
  24. Christopher W Lynn and Danielle S Bassett. 2019. The physics of brain network structure, function and control. Nature Reviews Physics 1, 5 (2019), 318–332.
  25. Deep anomaly detection of seizures with paired Stereoelectroencephalography and video recordings. Scientific Reports 11, 1 (2021), 1–11.
  26. Shuffle and learn: Unsupervised learning using temporal order verification. In ECCV. 527–544.
  27. Contrastive representation learning for Electroencephalogram classification. In PMLR. 238–253.
  28. Unified deep supervised domain adaptation and generalization. In ICCV. 5715–5725.
  29. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018).
  30. 11 - Magnetoelectric composites for medical application. In Composite Magnetoelectrics. Woodhead Publishing, 297–327.
  31. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS.
  32. Intracranial electroencephalographic seizure-onset patterns: Effect of underlying pathology. Brain 137, 1 (2014), 183–196.
  33. Predicting the spatiotemporal diversity of seizure propagation and termination in human focal epilepsy. Nature communications 9, 1 (2018), 1–15.
  34. Machine learning for predicting epileptic seizures using EEG signals: A review. IEEE Reviews in Biomedical Engineering 14 (2020), 139–155.
  35. Patrick Schäfer. 2015. The BOSS is concerned with time series classification in the presence of noise. Data Mining and Knowledge Discovery 29, 6 (2015), 1505–1530.
  36. The Temple University Hospital seizure detection corpus. Frontiers in Neuroinformatics 12 (2018), 83.
  37. Discrete graph structure learning for forecasting multiple time series. In ICLR.
  38. Epileptic seizures detection using deep learning techniques: A review. International Journal of Environmental Research and Public Health 18, 11 (2021), 5780.
  39. EEG emotion recognition using dynamical graph convolutional neural networks. IEEE Transactions on Affective Computing 11, 3 (2020), 532–541.
  40. Monash university, uea, ucr time series regression archive. arXiv preprint arXiv:2006.10996 (2020).
  41. Self-supervised graph neural networks for improved Electroencephalographic seizure analysis. In ICLR.
  42. Attention is all you need. In NeurIPS.
  43. Connectivity strength-weighted sparse group representation-based brain network construction for M CI classification. Human brain mapping 38, 5 (2017), 2370–2383.
  44. A multi-view deep learning framework for EEG seizure detection. IEEE Journal of Biomedical and Health Informatics 23, 1 (2019), 83–94.
  45. TS2Vec: Towards universal representation of time series. arXiv preprint arXiv:2106.10466 (2021).
  46. Graph Transformer networks. In NeurIPS.
  47. A Transformer-based framework for multivariate time series representation learning. In KDD. 2114–2124.
  48. A survey on deep learning-based non-invasive brain signals: Recent advances and new frontiers. Journal of Neural Engineering 18, 3 (2021), 031002.
  49. Graph-guided network for irregularly sampled multivariate time series. In ICLR.
  50. Zhe Zhu. 2017. Change detection using landsat time series: A review of frequencies, preprocessing, algorithms, and applications. ISPRS Journal of Photogrammetry and Remote Sensing 130 (2017), 370–384.
Citations (12)
View on Semantic Scholar

Summary

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

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