Linearizing Convolutional Neural Network improves P300 detection

Author(s): Ravindran, Sriram | Advisor(s): Sa, Virginia de | Abstract: P300 is an event-related potential evoked as a response to external stimuli. The P300-speller is a widely used BCI that has proven to be a reliable method in enabling people who cannot communicate via normal methods. Improving single-trial P300 classification helps increase communication bandwidth as it reduces the averaging process necessary to reduce noise. Deep learning approaches in this area have become more popular recently [2][3]. Certain architectural choices result in a better classifier. In this paper, we performed a study of EEGNet [2] as it performed well in our experiments. We report some improvements to the model. We also confirm that these suggestions improve other CNN based models by showing improved results with CNN-1 proposed in [4] on BCI Competition III Dataset II. We perform knowledge distillation of the resultant linear model into a logistic regression model and show that the model learns information similar but superior to LDA. We show that the logistic regression model obtained this way outperforms more complex models and is easy to interpret.

[1]  G. Pfurtscheller,et al.  The BCI competition III: validating alternative approaches to actual BCI problems , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Klaus-Robert Müller,et al.  Classifying Single Trial EEG: Towards Brain Computer Interfacing , 2001, NIPS.

[3]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[4]  Alain Rakotomamonjy,et al.  BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller , 2008, IEEE Transactions on Biomedical Engineering.

[5]  R. Srinivasan.  Methods to Improve the Spatial Resolution of EEG , 1999 .

[6]  Reza Fazel-Rezai,et al.  A region-based P300 speller for brain-computer interface , 2009, Canadian Journal of Electrical and Computer Engineering.

[7]  Marc M. Van Hulle,et al.  Comparison of Classification Methods for P300 Brain-Computer Interface on Disabled Subjects , 2011, Comput. Intell. Neurosci..

[8]  J. Wolpaw,et al.  A novel P300-based brain–computer interface stimulus presentation paradigm: Moving beyond rows and columns , 2010, Clinical Neurophysiology.

[9]  G. Pfurtscheller,et al.  Event-related dynamics of cortical rhythms: frequency-specific features and functional correlates. , 2001, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[10]  Stefan Haufe,et al.  On the interpretation of weight vectors of linear models in multivariate neuroimaging , 2014, NeuroImage.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[13]  Mahta Mousavi,et al.  Csp-NN: a Convolutional Neural Network Implementation of Common Spatial Patterns , 2017, GBCIC.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  H. Flor,et al.  The thought translation device (TTD) for completely paralyzed patients. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[16]  M R Nuwer,et al.  Continuous EEG monitoring in the intensive care unit: early findings and clinical efficacy. , 1999, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

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

[18]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Yann LeCun,et al.  Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG , 2008, 2008 IEEE Workshop on Machine Learning for Signal Processing.

[20]  C.W. Anderson,et al.  Comparison of linear, nonlinear, and feature selection methods for EEG signal classification , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  Guideline Thirteen: Guidelines for Standard Electrode Position Nomenclature , 1994, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[22]  D. Hubel,et al.  Receptive fields of single neurones in the cat's striate cortex , 1959, The Journal of physiology.

[23]  E. Donchin,et al.  Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. , 1988, Electroencephalography and clinical neurophysiology.

[24]  Ramesh Maddula,et al.  Deep Recurrent Convolutional Neural Networks for Classifying P300 BCI signals , 2017, GBCIC.

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

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

[27]  Kunihiko Fukushima,et al.  Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition , 1982 .

[28]  K. Strimmer,et al.  Statistical Applications in Genetics and Molecular Biology A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics , 2011 .

[29]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[30]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[31]  R. Fazel-Rezai,et al.  Analysis of P300 Classifiers in Brain Computer Interface Speller , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  R. Ilmoniemi,et al.  Magnetoencephalography-theory, instrumentation, and applications to noninvasive studies of the working human brain , 1993 .

[33]  J. Brunberg,et al.  Adult claustrophobia, anxiety and sedation in MRI. , 1997, Magnetic resonance imaging.

[34]  C. Herrmann.  Human EEG responses to 1–100 Hz flicker: resonance phenomena in visual cortex and their potential correlation to cognitive phenomena , 2001, Experimental Brain Research.

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

[36]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[37]  Young Bae Jun,et al.  Fuzzy soft set theory applied to BCK/BCI-algebras , 2010, Comput. Math. Appl..

[38]  T W Picton,et al.  The P300 Wave of the Human Event‐Related Potential , 1992, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[39]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[40]  C. Cinel,et al.  P300-Based BCI Mouse With Genetically-Optimized Analogue Control , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[41]  Vladimir Bostanov,et al.  BCI competition 2003-data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram , 2004, IEEE Transactions on Biomedical Engineering.

[42]  Brendan Z. Allison,et al.  P300 brain computer interface: current challenges and emerging trends , 2012, Front. Neuroeng..

[43]  Dean J Krusienski,et al.  A comparison of classification techniques for the P300 Speller , 2006, Journal of neural engineering.