Subject adaptation network for EEG data analysis

Abstract Biosignals tend to display manifest intra- and cross-subject variance, which generates numerous challenges for electroencephalograph (EEG) data analysis. For instance, in the context of classification, the discrepancy between EEG data can make the trained model generalising poorly for new test subjects. In this paper, a subject adaptation network (SAN) inspired by the generative adversarial network (GAN) to mitigate different variances is proposed for analysing EEG data. First the challenges faced by traditional approaches employed for EEG signal processing are emphasised. Then the problem is formulated from mathematical perspective to highlight the key points in resolving such discrepancies. Third, the motivation behind and design principle of the SAN are described in an intuitive manner to reflect its suitability for analysing EEG data. Then after depicting the overall architecture of the SAN, several experiments are used to justify the practicality and efficiency of using the proposed model from different perspectives. For instance, an EEG dataset captured during a stereotypical neurophysiological experiment called the VEP oddball task is utilised to demonstrate the performance improvement achieved by running the SAN.

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

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

[3]  Wei Liu,et al.  Continuous Vigilance Estimation Using LSTM Neural Networks , 2016, ICONIP.

[4]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[5]  Bianca Zadrozny,et al.  Learning and evaluating classifiers under sample selection bias , 2004, ICML.

[6]  Dongrui Wu,et al.  Sustained Attention Driving Task Analysis based on Recurrent Residual Neural Network using EEG Data , 2018, 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[7]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[8]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[9]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  M. Kawanabe,et al.  Direct importance estimation for covariate shift adaptation , 2008 .

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

[12]  Dongrui Wu,et al.  Online driver's drowsiness estimation using domain adaptation with model fusion , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

[13]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[14]  Trevor Darrell,et al.  Transferring Visual Category Models to New Domains , 2010 .

[15]  Chin-Teng Lin,et al.  Real-time assessment of vigilance level using an innovative Mindo4 wireless EEG system , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[16]  Saeid Sanei,et al.  EEG signal processing , 2000, Clinical Neurophysiology.

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

[18]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[19]  Brent Lance,et al.  Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[20]  James J. Jiang.  A Literature Survey on Domain Adaptation of Statistical Classifiers , 2007 .

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