Improved Techniques for Building EEG Feature Filters

Recent advances in the generative adversarial network (GAN) based image translation have shown its potential of being an image style transformer. Similarly, defined as a style transformer for physiological signals, a feature filter is used to filter privacy-related features while still keeping useful features. However, existing feature filter techniques have three problems: (1) the privacy-related features cannot be filtered out to the extent we need through a simple Conv-Deconv generator structure, and (2) the generator cannot control the semantics (maintain desired features) of given physiological signals. To address these problems, we utilize deeper neural networks and adopt techniques from domain adaptation. This includes semantic loss and a GAN based model structure with two generators, two discriminators and a classifier to form a game of five. Our results on the UCI EEG dataset demonstrate that our model can simultaneously (1) achieve the state-of-the-art accuracy removal for the privacy-related feature, (2) reduce the desired feature removal accuracy drop, and (3) make the filtered signals can be interpreted or visually checked.

[1]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[2]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[3]  Ming Zhou,et al.  Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study , 2018, ArXiv.

[4]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Mubarak Shah,et al.  Generative Adversarial Networks Conditioned by Brain Signals , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Fei Su,et al.  EEG-based Personal Identification: from Proof-of-Concept to A Practical System , 2010, 2010 20th International Conference on Pattern Recognition.

[8]  Mohammed Yeasin,et al.  Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks , 2015, ICLR.

[9]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[11]  Elizabeth B. Varghese,et al.  A novel approach for ensuring the privacy of EEG signals using application-specific feature extraction and AES algorithm , 2016, 2016 International Conference on Inventive Computation Technologies (ICICT).

[12]  Jiawei Yang,et al.  A Generalised Seizure Prediction with Convolutional Neural Networks for Intracranial and Scalp Electroencephalogram Data Analysis , 2017, ArXiv.

[13]  François Laviolette,et al.  Domain-Adversarial Neural Networks , 2014, ArXiv.

[14]  Chong Jin Ong,et al.  Automatic EEG Artifact Removal: A Weighted Support Vector Machine Approach With Error Correction , 2009, IEEE Transactions on Biomedical Engineering.

[15]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[16]  Begoña Garcia-Zapirain,et al.  EEG artifact removal—state-of-the-art and guidelines , 2015, Journal of neural engineering.

[17]  Jian Shen,et al.  Adversarial Representation Learning for Domain Adaptation , 2017, ArXiv.

[18]  Samaher Al-Janabi,et al.  Survey of main challenges (security and privacy) in wireless body area networks for healthcare applications , 2017 .

[19]  Kaushik Sundararajan,et al.  Privacy and security issues in Brain Computer Interfaces , 2018 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[22]  Tim Oates,et al.  Denoising Time Series Data Using Asymmetric Generative Adversarial Networks , 2018, PAKDD.

[23]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[24]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[25]  Qiang Ji,et al.  Cross-subject workload classification with a hierarchical Bayes model , 2012, NeuroImage.

[26]  Alois Schlögl.  An overview on data formats for biomedical signals , 2009 .

[27]  Brian Roark,et al.  RSVP keyboard: An EEG based typing interface , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[28]  Tamás D. Gedeon,et al.  Deep Feature Learning and Visualization for EEG Recording Using Autoencoders , 2018, ICONIP.

[29]  Tom Gedeon,et al.  Generalized Alignment for Multimodal Physiological Signal Learning , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[30]  Miguel A. L. Nicolelis,et al.  Brain–machine interfaces: past, present and future , 2006, Trends in Neurosciences.

[31]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[32]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[33]  Bernhard Schölkopf,et al.  Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces , 2005, EURASIP J. Adv. Signal Process..

[34]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[35]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  J. Kulynych,et al.  Legal and ethical issues in neuroimaging research: human subjects protection, medical privacy, and the public communication of research results , 2002, Brain and Cognition.