Improving P300 Speller performance by means of optimization and machine learning

Brain-Computer Interfaces (BCIs) are systems allowing people to interact with the environment bypassing the natural neuromuscular and hormonal outputs of the peripheral nervous system (PNS). These interfaces record a user's brain activity and translate it into control commands for external devices, thus providing the PNS with additional artificial outputs. In this framework, the BCIs based on the P300 Event-Related Potentials (ERP), which represent the electrical responses recorded from the brain after specific events or stimuli, have proven to be particularly successful and robust. The presence or the absence of a P300 evoked potential within the EEG features is determined through a classification algorithm. Linear classifiers such as SWLDA and SVM are the most used for ERPs' classification. Due to the low signal-to-noise ratio of the EEG signals, multiple stimulation sequences (a.k.a. iterations) are carried out and then averaged before the signals being classified. However, while augmenting the number of iterations improves the Signal-to-Noise Ratio (SNR), it also slows down the process. In the early studies, the number of iterations was fixed (no stopping), but recently, several early stopping strategies have been proposed in the literature to dynamically interrupt the stimulation sequence when a certain criterion is met to enhance the communication rate. In this work, we explore how to improve the classification performances in P300 based BCIs by combining optimization and machine learning. First, we propose a new decision function that aims at improving classification performances in terms of accuracy and Information Transfer Rate both in a no stopping and early stopping environment. Then, we propose a new SVM training problem that aims to facilitate the target-detection process. Our approach proves to be effective on several publicly available datasets.

[1]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[2]  Benjamin Blankertz,et al.  Two-dimensional auditory p300 speller with predictive text system , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[3]  Benjamin Blankertz,et al.  Exploring motion VEPs for gaze-independent communication , 2012, Journal of neural engineering.

[4]  Chih-Jen Lin,et al.  A dual coordinate descent method for large-scale linear SVM , 2008, ICML '08.

[5]  Stefan Haufe,et al.  Optimizing event-related potential based brain-computer interfaces: a systematic evaluation of dynamic stopping methods. , 2013, Journal of neural engineering.

[6]  Cuntai Guan,et al.  Asynchronous P300-Based Brain--Computer Interfaces: A Computational Approach With Statistical Models , 2008, IEEE Transactions on Biomedical Engineering.

[7]  Lucia Rita Quitadamo,et al.  Describing Different Brain Computer Interface Systems Through a Unique Model: A UML Implementation , 2008, Neuroinformatics.

[8]  A. Lenhardt,et al.  An Adaptive P300-Based Online Brain–Computer Interface , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  J. Wolpaw,et al.  Brain-Computer Interfaces: Principles and Practice , 2012 .

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

[11]  F. Cincotti,et al.  Attention and P300-based BCI performance in people with amyotrophic lateral sclerosis , 2013, Front. Hum. Neurosci..

[12]  J. Wolpaw,et al.  A P300 event-related potential brain–computer interface (BCI): The effects of matrix size and inter stimulus interval on performance , 2006, Biological Psychology.

[13]  Eryk Dutkiewicz,et al.  Subject-Independent P300 BCI Using Ensemble Classifier, Dynamic Stopping and Adaptive Learning , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[14]  Marco Sciandrone,et al.  Nonlinear optimization and support vector machines , 2018, 4OR.

[15]  V. Sinha,et al.  Event-related potential: An overview , 2009, Industrial psychiatry journal.

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

[17]  G Pfurtscheller,et al.  EEG-based communication: improved accuracy by response verification. , 1998, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[18]  M S Treder,et al.  Gaze-independent brain–computer interfaces based on covert attention and feature attention , 2011, Journal of neural engineering.

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

[20]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update , 2018, Journal of neural engineering.

[21]  B. Blankertz,et al.  (C)overt attention and visual speller design in an ERP-based brain-computer interface , 2010, Behavioral and Brain Functions.

[22]  Fabien Lotte,et al.  A Tutorial on EEG Signal Processing Techniques for Mental State Recognition in Brain-Computer Interfaces , 2014 .

[23]  J. Wolpaw,et al.  P300-based brain-computer interface (BCI) event-related potentials (ERPs): People with amyotrophic lateral sclerosis (ALS) vs. age-matched controls , 2015, Clinical Neurophysiology.

[24]  Luigi Bianchi,et al.  The NPXLab suite 2018: A free features rich set of tools for the analysis of neuro-electric signals , 2018 .

[25]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[26]  Dong Ming,et al.  Incorporation of dynamic stopping strategy into the high-speed SSVEP-based BCIs , 2018, Journal of neural engineering.

[27]  Leslie M. Collins,et al.  Utilizing a Language Model to Improve Online Dynamic Data Collection in P300 Spellers , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[28]  Eryk Dutkiewicz,et al.  Subject-Independent ERP-Based Brain–Computer Interfaces , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  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.

[30]  K. A. Colwell,et al.  Bayesian Approach to Dynamically Controlling Data Collection in P300 Spellers , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[31]  F Cincotti,et al.  Influence of P300 latency jitter on event related potential-based brain–computer interface performance , 2014, Journal of neural engineering.

[32]  Richard F. Gunst,et al.  Applied Regression Analysis , 1999, Technometrics.

[33]  Xingyu Wang,et al.  An adaptive P300-based control system , 2011, Journal of neural engineering.

[34]  Shangkai Gao,et al.  An online brain–computer interface using non-flashing visual evoked potentials , 2010, Journal of neural engineering.

[35]  Luigi Bianchi,et al.  A New Early Stopping Method for P300 Spellers , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[36]  Michael Tangermann,et al.  Listen, You are Writing! Speeding up Online Spelling with a Dynamic Auditory BCI , 2011, Front. Neurosci..