EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate

OBJECTIVE Automatic measurement and monitoring of mental fatigue are invaluable for preventing mental-fatigue related accidents. We test an EEG-based mental-fatigue monitoring system using a probabilistic-based support vector-machines (SVM) method. METHODS Ten subjects underwent 25-h sleep deprivation experiments with EEG monitoring. EEG data were segmented into 3-s long epochs and manually classified into 5 mental-fatigue levels, based on subjects' performance on an auditory vigilance task (AVT). Probabilistic-based multi-class SVM and standard multi-class SVM were compared as classifiers for distinguishing mental fatigue into the 5 mental-fatigue levels. RESULTS Accuracy of the probabilistic-based multi-class SVM was 87.2%, compared to 85.4% using the standard multi-class SVM. Using confidence estimates aggregation, accuracy increased to 91.2%. CONCLUSIONS Probabilistic-based multi-class SVM not only gives superior classification accuracy but also provides a valuable estimate of confidence in the prediction of mental fatigue level in a given 3-s EEG epoch. SIGNIFICANCE The work demonstrates the feasibility of an automatic EEG method for assessing and monitoring of mental fatigue. Future applications of this include traffic safety and other domains where measurement or monitoring of mental fatigue is crucial.

[1]  S. Sathiya Keerthi,et al.  Which Is the Best Multiclass SVM Method? An Empirical Study , 2005, Multiple Classifier Systems.

[2]  A. Wirz-Justice,et al.  Power density in theta/alpha frequencies of the waking EEG progressively increases during sustained wakefulness. , 1995, Sleep.

[3]  T. Sejnowski,et al.  Estimating alertness from the EEG power spectrum , 1997, IEEE Transactions on Biomedical Engineering.

[4]  H. Jasper.  Report of the committee on methods of clinical examination in electroencephalography , 1958 .

[5]  Mercedes Atienza,et al.  Spectral and Topographic Microstructure of Brain Alpha Activity During Drowsiness at Sleep Onset and REM Sleep , 2000 .

[6]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[7]  Robert Du,et al.  Towards measurement of brain function in operational environments , 1995, Biological Psychology.

[8]  Lionel Tarassenko,et al.  Neural Network Analysis of the Mastoid EEG for the Assessment of Vigilance , 2004, Int. J. Hum. Comput. Interact..

[9]  C. Shapiro,et al.  Development of an adjective checklist to measure five FACES of fatigue and sleepiness. Data from a national survey of insomniacs. , 2002, Journal of psychosomatic research.

[10]  Kyoko Idogawa.  ON THE BRAIN WAVE ACTIVITY OF PROFESSIONAL DRIVERS DURING MONOTONOUS WORK , 1991 .

[11]  J. S. Weiner,et al.  Fitting the Task to the Man—An Ergonomic Approach , 1971 .

[12]  Andrew C. N. Chen,et al.  Automatic recognition of alertness and drowsiness from EEG by an artificial neural network. , 2002, Medical engineering & physics.

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  Y.Y. Pang,et al.  An Auditory Vigilance Task for Mental Fatigue Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[15]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[16]  D. Dinges.  An overview of sleepiness and accidents , 1995, Journal of sleep research.

[17]  Chong Jin Ong,et al.  A Feature Selection Method for Multilevel Mental Fatigue EEG Classification , 2007, IEEE Transactions on Biomedical Engineering.

[18]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[19]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[20]  Roman Rosipal,et al.  EEG-Based Estimation of Mental Fatigue: Convergent Evidence for a Three-State Model , 2007, HCI.

[21]  C. Gottfries,et al.  A rating scale for fibromyalgia and chronic fatigue syndrome (the FibroFatigue scale). , 2002, Journal of psychosomatic research.

[22]  R.D. Jones,et al.  Investigation of lapses of consciousness using a tracking task: preliminary results , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  Alan V. Oppenheim,et al.  Discrete-time Signal Processing. Vol.2 , 2001 .

[24]  Richard D. Jones.  Measurement of Sensory-Motor Control Performance Capacities: Tracking Tasks , 1999 .

[25]  Alan V. Oppenheim,et al.  Discrete-Time Signal Pro-cessing , 1989 .

[26]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[27]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[28]  C. Alloway,et al.  The alpha attenuation test: assessing excessive daytime sleepiness in narcolepsy-cataplexy. , 1997, Sleep.

[29]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[30]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[31]  R E Slaughter,et al.  The revised Piper Fatigue Scale: psychometric evaluation in women with breast cancer. , 1998, Oncology nursing forum.

[32]  Alexander J. Smola,et al.  Advances in Large Margin Classifiers , 2000 .

[33]  T. Sejnowski,et al.  Awareness during drowsiness: dynamics and electrophysiological correlates. , 2000, Canadian journal of experimental psychology = Revue canadienne de psychologie experimentale.

[34]  C. Stampi,et al.  A new quantitative method for assessing sleepiness: The alpha attenuation test , 1995 .

[35]  Chong Jin Ong,et al.  Feature selection via sensitivity analysis of SVM probabilistic outputs , 2008, 2008 IEEE International Conference on Systems, Man and Cybernetics.

[36]  Michel Martinez,et al.  Most Wanted , 2005 .

[37]  C Tarriere,et al.  AN ON-BOARD SYSTEM FOR DETECTING LAPSES OF ALERTNESS IN CAR DRIVING , 1995 .

[38]  Ashley Craig,et al.  Development of an algorithm for an EEG-based driver fatigue countermeasure. , 2003, Journal of safety research.

[39]  T. Åkerstedt,et al.  Sleepiness on the job: continuously measured EEG changes in train drivers. , 1987, Electroencephalography and clinical neurophysiology.

[40]  E. N. Corlett,et al.  BooksFitting the task to the man — An ergonomic approach (3rd Ed): E. Grandjean Taylor & Francis Ltd, London, pp 375 & ix, £14.50 (£9.50 paper) , 1980 .

[41]  D. Dijk,et al.  Frontal predominance of a relative increase in sleep delta and theta EEG activity after sleep loss in humans. , 1999, Sleep research online : SRO.

[42]  Melissa M. Mallis,et al.  MANAGING FATIGUE BY DROWSINESS DETECTION: CAN TECHNOLOGICAL PROMISES BE REALIZED? , 1998 .

[43]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

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

[45]  Thomas G. Dietterich,et al.  Editors. Advances in Neural Information Processing Systems , 2002 .

[46]  David F. Dinges,et al.  Microcomputer analyses of performance on a portable, simple visual RT task during sustained operations , 1985 .

[47]  S. Lahiri.  Resampling Methods for Dependent Data , 2003 .

[48]  David G. Stork,et al.  Pattern Classification , 1973 .

[49]  Gregory Belenky,et al.  The Walter Reed palm-held psychomotor vigilance test , 2005, Behavior research methods.

[50]  H.,et al.  Neural Network Analysis of Steel Plate , 2007 .

[51]  A. Craig,et al.  A critical review of the psychophysiology of driver fatigue , 2001, Biological Psychology.

[52]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.