Real-time Mental State Recognition using a Wearable EEG

The increasing quality and availability of low-cost EEG systems offer new possibilities for non-medical purposes. Existing openly available algorithms to assess the user’s mental state in real-time have been mainly performed with medical-grade equipment. In this paper, an approach to assess the user’s Focus or Relax states in real-time using a consumer-grade, wearable EEG headband is evaluated. One naive measure and four entropy-based measures, computed using relative frequency band powers in the EEG signal, were introduced. Classifiers for relax and focus state detection, based on the estimation of probability distributions, were developed and evaluated in a user study. Results showed that the Tsallis entropy-based measure performed best for the Focus score, whereas the Renyi measure performed best for the Relax score. Sensitivities of 82.0% and 80.4% with specificities of 82.8% and 80.8% were achieved for the Focus and Relax scores, respectively. The results demonstrated the possibilities of using a wearable EEG system for real-time mental state recognition.

[1]  Judith Amores,et al.  PsychicVR: Increasing mindfulness by using Virtual Reality and Brain Computer Interfaces , 2016, CHI Extended Abstracts.

[2]  N. Thakor,et al.  Parameterized entropy analysis of EEG following hypoxic–ischemic brain injury , 2003 .

[3]  Simon P. Kelly,et al.  Visual spatial attention control in an independent brain-computer interface , 2005, IEEE Transactions on Biomedical Engineering.

[4]  Imrich Chlamtac,et al.  The P2 algorithm for dynamic calculation of quantiles and histograms without storing observations , 1985, CACM.

[5]  Nitish V. Thakor,et al.  EEG Signal Processing: Theory and Applications , 2020, Neural Engineering.

[6]  R. Ulrich.  Natural Versus Urban Scenes , 1981 .

[7]  Christopher J. Honey,et al.  Future trends in Neuroimaging: Neural processes as expressed within real-life contexts , 2012, NeuroImage.

[8]  Klaus-Robert Müller,et al.  Machine learning for real-time single-trial EEG-analysis: From brain–computer interfacing to mental state monitoring , 2008, Journal of Neuroscience Methods.

[9]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[10]  Pouya Bashivan,et al.  Mental State Recognition via Wearable EEG , 2016, ArXiv.

[11]  G. Buzsáki.  Rhythms of the brain , 2006 .

[12]  D. Schacter.  EEG theta waves and psychological phenomena: A review and analysis , 1977, Biological Psychology.

[13]  Evangelos Bekiaris,et al.  Using EEG spectral components to assess algorithms for detecting fatigue , 2009, Expert Syst. Appl..

[14]  S. Kar,et al.  EEG signal analysis for the assessment and quantification of driver’s fatigue , 2010 .

[15]  Lorenzo Chiari,et al.  The origin of Biopotentials , 2012 .

[16]  W. Klimesch.  EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis , 1999, Brain Research Reviews.

[17]  T. Fernández,et al.  EEG activation patterns during the performance of tasks involving different components of mental calculation. , 1995, Electroencephalography and clinical neurophysiology.