A few filters are enough: Convolutional Neural Network for P300 Detection

Over the past decade, convolutional neural networks (CNNs) have become the driving force of an ever-increasing set of applications, achieving state-of-the-art performance. Most of the modern CNN architectures are composed of many convolutional and fully connected layers and typically require thousands or millions of parameters to learn. CNNs have also been effective in the detection of Event-Related Potentials from electroencephalogram (EEG) signals, notably the P300 component which is frequently employed in Brain-Computer Interfaces (BCIs). However, for this task, the increase in detection rates compared to approaches based on human-engineered features has not been as impressive as in other areas and might not justify such a large number of parameters. In this paper, we study the performances of existing CNN architectures with diverse complexities for single-trial within-subject and cross-subject P300 detection on four different datasets. We also proposed SepConv1D, a very simple CNN architecture consisting of a single depthwise separable 1D convolutional layer followed by a fully connected Sigmoid classification neuron. We found that with as few as four filters in its convolutional layer and a small overall number of parameters, SepConv1D obtained competitive performances in the four datasets. We believe this may represent an important step towards building simpler, cheaper, faster, and more portable BCIs.

[1]  Frank Kirchner,et al.  An Adaptive Spatial Filter for User-Independent Single Trial Detection of Event-Related Potentials , 2015, IEEE Transactions on Biomedical Engineering.

[2]  Tiago H. Falk,et al.  Deep learning-based electroencephalography analysis: a systematic review , 2019, Journal of neural engineering.

[3]  Martin Spüler,et al.  Error-related potentials during continuous feedback: using EEG to detect errors of different type and severity , 2015, Front. Hum. Neurosci..

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

[5]  Tom Chau,et al.  Partially supervised P300 speller adaptation for eventual stimulus timing optimization: target confidence is superior to error-related potential score as an uncertain label. , 2016, Journal of neural engineering.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[8]  Wei Wu,et al.  Deep learning based on Batch Normalization for P300 signal detection , 2018, Neurocomputing.

[9]  Yu Liu,et al.  A Simple Convolutional Neural Network for Accurate P300 Detection and Character Spelling in Brain Computer Interface , 2018, IJCAI.

[10]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[11]  E Donchin,et al.  The mental prosthesis: assessing the speed of a P300-based brain-computer interface. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[12]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

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

[15]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[17]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update , 2018, 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]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[20]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[21]  Ian H. Witten,et al.  Chapter 10 – Deep learning , 2017 .

[22]  Laurent Bougrain,et al.  An Open-Access P300 Speller Database , 2010 .

[23]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[24]  Rajesh P. N. Rao,et al.  Cortical Topography of Error-Related High-Frequency Potentials During Erroneous Control in a Continuous Control Brain–Computer Interface , 2019, Front. Neurosci..

[25]  Ernesto Bribiesca,et al.  P300 Detection Based on EEG Shape Features , 2016, Comput. Math. Methods Medicine.

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

[27]  Cheng-Jian Lin,et al.  Classification of mental task from EEG data using neural networks based on particle swarm optimization , 2009, Neurocomputing.

[28]  Clemens Brunner,et al.  BNCI Horizon -- The Future of Brain/Neural Computer Interaction: Horizon 2020 , 2014 .

[29]  A. Walker.  Electroencephalography, Basic Principles, Clinical Applications and Related Fields , 1982 .

[30]  Alexandre Barachant,et al.  Brain-computer interface for the communication of acute patients: a feasibility study and a randomized controlled trial comparing performance with healthy participants and a traditional assistive device , 2016 .

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

[32]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[33]  Fabien Lotte,et al.  Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces , 2015, Proceedings of the IEEE.

[34]  Helge J. Ritter,et al.  BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm , 2004, IEEE Transactions on Biomedical Engineering.

[35]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

[36]  Rami J. Oweis,et al.  Investigation of a wavelet-based neural network learning algorithm applied to P300 based brain-computer interface , 2018 .

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

[38]  Yanina Atum,et al.  Genetic feature selection to optimally detect P300 in brain computer interfaces , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[39]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[40]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[41]  J. Polich,et al.  Neuropsychology and neuropharmacology of P3a and P3b. , 2006, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[42]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[43]  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.

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

[45]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[46]  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.