Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DTP-Net: Learning to Reconstruct EEG signals in Time-Frequency Domain by Multi-scale Feature Reuse (2312.09417v2)

Published 27 Nov 2023 in eess.SP and cs.LG

Abstract: Electroencephalography (EEG) signals are easily corrupted by various artifacts, making artifact removal crucial for improving signal quality in scenarios such as disease diagnosis and brain-computer interface (BCI). In this paper, we present a fully convolutional neural architecture, called DTP-Net, which consists of a Densely Connected Temporal Pyramid (DTP) sandwiched between a pair of learnable time-frequency transformations for end-to-end electroencephalogram (EEG) denoising. The proposed method first transforms a single-channel EEG signal of arbitrary length into the time-frequency domain via an Encoder layer. Then, noises, such as ocular and muscle artifacts, are extracted by DTP in a multi-scale fashion and reduced. Finally, a Decoder layer is employed to reconstruct the artifact-reduced EEG signal. Additionally, we conduct an in-depth analysis of the representation learning behavior of each module in DTP-Net to substantiate its robustness and reliability. Extensive experiments conducted on two public semi-simulated datasets demonstrate the effective artifact removal performance of DTP-Net, which outperforms state-of-art approaches. Experimental results demonstrate cleaner waveforms and significant improvement in Signal-to-Noise Ratio (SNR) and Relative Root Mean Square Error (RRMSE) after denoised by the proposed model. Moreover, the proposed DTP-Net is applied in a specific BCI downstream task, improving the classification accuracy by up to 5.55% compared to that of the raw signals, validating its potential applications in the fields of EEG-based neuroscience and neuro-engineering.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Toward open-world electroencephalogram decoding via deep learning: A comprehensive survey. IEEE Signal Processing Magazine, 39(2):117–134, 2022. doi:10.1109/msp.2021.3134629. URL https://doi.org/10.1109/msp.2021.3134629.
  2. Donald L. Schomer and Fernando H. Lopes da Silva, editors. Niedermeyer's Electroencephalography. Oxford University Press, November 2017. doi:10.1093/med/9780190228484.001.0001. URL https://doi.org/10.1093/med/9780190228484.001.0001.
  3. Removal of artifacts from EEG signals: A review. Sensors, 19(5):987, February 2019. doi:10.3390/s19050987. URL https://doi.org/10.3390/s19050987.
  4. Independent component analysis of electroencephalographic and event-related potential data. In Central Auditory Processing and Neural Modeling, pages 189–197. Springer US, 1998. doi:10.1007/978-1-4615-5351-9_17. URL https://doi.org/10.1007/978-1-4615-5351-9_17.
  5. Identification and removal of physiological artifacts from electroencephalogram signals: A review. IEEE Access, 6:30630–30652, 2018. doi:10.1109/access.2018.2842082. URL https://doi.org/10.1109/access.2018.2842082.
  6. Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram. IEEE Transactions on Biomedical Engineering, 53(12):2583–2587, November 2006. doi:10.1109/tbme.2006.879459. URL https://doi.org/10.1109/tbme.2006.879459.
  7. Review of challenges associated with the EEG artifact removal methods. Biomedical Signal Processing and Control, 68:102741, July 2021. doi:10.1016/j.bspc.2021.102741. URL https://doi.org/10.1016/j.bspc.2021.102741.
  8. Wavelet-ICA methodology for efficient artifact removal from electroencephalographic recordings. In 2007 International Joint Conference on Neural Networks. IEEE, August 2007. doi:10.1109/ijcnn.2007.4371184. URL https://doi.org/10.1109/ijcnn.2007.4371184.
  9. The use of ensemble empirical mode decomposition with canonical correlation analysis as a novel artifact removal technique. IEEE Transactions on Biomedical Engineering, 60(1):97–105, January 2013. doi:10.1109/tbme.2012.2225427. URL https://doi.org/10.1109/tbme.2012.2225427.
  10. EOG artifact removal using a wavelet neural network. Neurocomputing, 97:374–389, November 2012. doi:10.1016/j.neucom.2012.04.016. URL https://doi.org/10.1016/j.neucom.2012.04.016.
  11. Automated eye blink artefact removal from EEG using support vector machine and autoencoder. IET Signal Processing, 13(2):141–148, April 2019. doi:10.1049/iet-spr.2018.5111. URL https://doi.org/10.1049/iet-spr.2018.5111.
  12. Automatic ocular artifacts removal in EEG using deep learning. Biomedical Signal Processing and Control, 43:148–158, May 2018. doi:10.1016/j.bspc.2018.02.021. URL https://doi.org/10.1016/j.bspc.2018.02.021.
  13. EEGANet: Removal of ocular artifacts from the EEG signal using generative adversarial networks. IEEE Journal of Biomedical and Health Informatics, 26(10):4913–4924, October 2022. doi:10.1109/jbhi.2021.3131104. URL https://doi.org/10.1109/jbhi.2021.3131104.
  14. Denoising EEG signals for real-world BCI applications using GANs. Frontiers in Neuroergonomics, 2, January 2022. doi:10.3389/fnrgo.2021.805573. URL https://doi.org/10.3389/fnrgo.2021.805573.
  15. A novel end-to-end 1d-ResCNN model to remove artifact from EEG signals. Neurocomputing, 404:108–121, September 2020. doi:10.1016/j.neucom.2020.04.029. URL https://doi.org/10.1016/j.neucom.2020.04.029.
  16. EEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising. Journal of Neural Engineering, 18(5):056057, October 2021a. doi:10.1088/1741-2552/ac2bf8. URL https://doi.org/10.1088/1741-2552/ac2bf8.
  17. Frequency information enhanced deep EEG denoising network for ocular artifact removal. IEEE Sensors Journal, pages 1–1, 2022. doi:10.1109/jsen.2022.3209805. URL https://doi.org/10.1109/jsen.2022.3209805.
  18. EEG reconstruction with a dual-scale CNN-LSTM model for deep artifact removal. IEEE Journal of Biomedical and Health Informatics, pages 1–12, 2022. doi:10.1109/jbhi.2022.3227320. URL https://doi.org/10.1109/jbhi.2022.3227320.
  19. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
  20. A semi-simulated EEG/EOG dataset for the comparison of EOG artifact rejection techniques. Data in Brief, 8:1004–1006, September 2016. doi:10.1016/j.dib.2016.06.032. URL https://doi.org/10.1016/j.dib.2016.06.032.
  21. Source separation from single-channel recordings by combining empirical-mode decomposition and independent component analysis. IEEE Transactions on Biomedical Engineering, 57(9):2188–2196, September 2010. doi:10.1109/tbme.2010.2051440. URL https://doi.org/10.1109/tbme.2010.2051440.
  22. A novel convolutional neural network model to remove muscle artifacts from EEG. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, June 2021b. doi:10.1109/icassp39728.2021.9414228. URL https://doi.org/10.1109/icassp39728.2021.9414228.
  23. A novel multimodule neural network for EEG denoising. IEEE Access, 10:49528–49541, 2022. doi:10.1109/access.2022.3173261. URL https://doi.org/10.1109/access.2022.3173261.
  24. IC-u-net: A u-net-based denoising autoencoder using mixtures of independent components for automatic EEG artifact removal. NeuroImage, 263:119586, November 2022. doi:10.1016/j.neuroimage.2022.119586. URL https://doi.org/10.1016/j.neuroimage.2022.119586.
  25. Non-local u-nets for biomedical image segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, 2020.
  26. Learning end-to-end phase retrieval using only one interferogram with mixed-context network. In Gabriel Popescu, YongKeun Park, and Yang Liu, editors, Quantitative Phase Imaging VIII. SPIE, March 2022. doi:10.1117/12.2610502. URL https://doi.org/10.1117/12.2610502.
  27. U-net: Convolutional networks for biomedical image segmentation, 2015.
  28. Multi-scale context aggregation by dilated convolutions. In International Conference on Learning Representations, 2016.
  29. Review of the bci competition iv. Frontiers in Neuroscience, 6, 2012. ISSN 1662-4548. doi:10.3389/fnins.2012.00055. URL http://dx.doi.org/10.3389/fnins.2012.00055.
  30. Kinesthesia in a sustained-attention driving task. NeuroImage, 91:187–202, May 2014. ISSN 1053-8119. doi:10.1016/j.neuroimage.2014.01.015. URL http://dx.doi.org/10.1016/j.neuroimage.2014.01.015.
  31. Photo-realistic single image super-resolution using a generative adversarial network. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, July 2017. doi:10.1109/cvpr.2017.19. URL http://dx.doi.org/10.1109/CVPR.2017.19.
  32. Multiresolution decomposition of non-stationary eeg signals: A preliminary study. Computers in Biology and Medicine, 25(4):373–382, July 1995. ISSN 0010-4825. doi:10.1016/0010-4825(95)00014-u. URL http://dx.doi.org/10.1016/0010-4825(95)00014-U.
  33. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res., 11:3371–3408, dec 2010. ISSN 1532-4435.
  34. Objective and subjective evaluation of online error correction during p300-based spelling. Advances in Human-Computer Interaction, 2012:1–13, 2012. ISSN 1687-5907. doi:10.1155/2012/578295. URL http://dx.doi.org/10.1155/2012/578295.
  35. Multimodal signal dataset for 11 intuitive movement tasks from single upper extremity during multiple recording sessions. GigaScience, 9(10), October 2020. ISSN 2047-217X. doi:10.1093/gigascience/giaa098. URL http://dx.doi.org/10.1093/gigascience/giaa098.
  36. The non-invasive berlin brain–computer interface: Fast acquisition of effective performance in untrained subjects. NeuroImage, 37(2):539–550, August 2007. ISSN 1053-8119. doi:10.1016/j.neuroimage.2007.01.051. URL http://dx.doi.org/10.1016/j.neuroimage.2007.01.051.
  37. Deeply-Supervised Nets. In Guy Lebanon and S. V. N. Vishwanathan, editors, Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, volume 38 of Proceedings of Machine Learning Research, pages 562–570, San Diego, California, USA, 09–12 May 2015. PMLR. URL https://proceedings.mlr.press/v38/lee15a.html.
  38. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, December 2015. doi:10.1109/iccv.2015.123. URL https://doi.org/10.1109/iccv.2015.123.
  39. Training behavior of deep neural network in frequency domain. In Neural Information Processing, pages 264–274. Springer International Publishing, 2019. doi:10.1007/978-3-030-36708-4_22. URL https://doi.org/10.1007/978-3-030-36708-4_22.
  40. Removal of ocular artifacts from the EEG — a biophysical approach to the EOG. Electroencephalography and Clinical Neurophysiology, 60(5):455–463, May 1985. doi:10.1016/0013-4694(85)91020-x. URL https://doi.org/10.1016/0013-4694(85)91020-x.
  41. Adaptive single-channel EEG artifact removal with applications to clinical monitoring. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30:286–295, 2022. doi:10.1109/tnsre.2022.3147072. URL https://doi.org/10.1109/tnsre.2022.3147072.
  42. pyriemann/pyriemann: v0.3, July 2022. URL https://doi.org/10.5281/zenodo.7547583.
  43. W.Luo. xai-kit. URL https://github.com/williamro/xai-kit.
  44. Residual connections encourage iterative inference. In International Conference on Learning Representations, 2018. URL https://openreview.net/forum?id=SJa9iHgAZ.
Citations (1)
View on Semantic Scholar

Summary

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

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