Drowsiness detection for single channel EEG by DWT best m-term approximation

Introduction In this paper we propose a promising new technique for drowsiness detection. It consists of applying the best m-term approximation on a single-channel electroencephalography (EEG) signal preprocessed through a discrete wavelet transform. Methods In order to classify EEG epochs as awake or drowsy states, the most significant m terms from the wavelet expansion of an EEG signal are selected according to the magnitude of their coefficients related to the alpha and beta rhythms. Results By using a simple thresholding strategy it provides hit rates comparable to those using more complex techniques. It was tested on a set of 6 hours and 50 minutes EEG drowsiness signals from PhysioNet Sleep Database yielding an overall sensitivity (TPR) of 84.98% and 98.65% of precision (PPV). Conclusion The method has proved itself efficient at separating data from different brain rhythms, thus alleviating the requirement for complex post-processing classification algorithms.

[1]  Zizhong Chen,et al.  A survey of power and energy efficient techniques for high performance numerical linear algebra operations , 2014, Parallel Comput..

[2]  A. Avidan,et al.  Review of Sleep Medicine , 2002 .

[3]  Agustina Garcés Correa,et al.  An automatic detector of drowsiness based on spectral analysis and wavelet decomposition of EEG records , 2010, EMBC 2010.

[4]  E. Basar,et al.  Wavelet entropy: a new tool for analysis of short duration brain electrical signals , 2001, Journal of Neuroscience Methods.

[5]  Ole Møller Nielsen,et al.  Wavelets in scientific computing , 1998 .

[6]  Chin-Teng Lin,et al.  A Real-Time Wireless Brain–Computer Interface System for Drowsiness Detection , 2010, IEEE Transactions on Biomedical Circuits and Systems.

[7]  Yi Wang,et al.  PI3K/Akt-independent negative regulation of JNK signaling by MKP-7 after cerebral ischemia in rat hippocampus , 2013, BMC Neuroscience.

[8]  A. Craig,et al.  Electroencephalography Activity Associated with Driver Fatigue: Implications for a Fatigue Countermeasure Device , 2001 .

[9]  Y.C. Chen,et al.  Monitoring Driver's Alertness Based on the Driving Performance Estimation and the EEG Power Spectrum Analysis , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[10]  Tzyy-Ping Jung,et al.  EEG-based drowsiness estimation for safety driving using independent component analysis , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[11]  R. Coifman,et al.  Fast wavelet transforms and numerical algorithms I , 1991 .

[12]  Vladimir N. Temlyakov,et al.  Nonlinear Methods of Approximation , 2003, Found. Comput. Math..

[13]  Abdulhamit Subasi,et al.  Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients , 2005, Expert Syst. Appl..

[14]  Margaret M. Peden,et al.  World Report on Road Traffic Injury Prevention , 2004 .

[15]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  P. Achermann,et al.  A new method for detecting state changes in the EEG: exploratory application to sleep data , 1998, Journal of sleep research.

[17]  Truong Q. Nguyen,et al.  Wavelets and filter banks , 1996 .

[18]  A. Medl,et al.  Time Frequency and Wavelets in Biomedical Signal Processing , 1998, IEEE Engineering in Medicine and Biology Magazine.

[19]  Chrysoula Kourtidou-Papadeli,et al.  Monitoring sleepiness with on-board electrophysiological recordings for preventing sleep-deprived traffic accidents , 2007, Clinical Neurophysiology.

[20]  David Salesin,et al.  Wavelets for computer graphics: a primer.1 , 1995, IEEE Computer Graphics and Applications.

[21]  Mervyn V. M. Yeo,et al.  Characteristic EEG differences between voluntary recumbent sleep onset in bed and involuntary sleep onset in a driving simulator , 2007, Clinical Neurophysiology.

[22]  Yu-Liang Hsu,et al.  Automatic sleep stage recurrent neural classifier using energy features of EEG signals , 2013, Neurocomputing.

[23]  F Ferrillo,et al.  A method for the automatic detection of arousals during sleep. , 1999, Sleep.

[24]  Rakesh Kumar Sinha,et al.  Artificial Neural Network and Wavelet Based Automated Detection of Sleep Spindles, REM Sleep and Wake States , 2008, Journal of Medical Systems.

[25]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[26]  E. J. Stollnitz,et al.  Wavelets for Computer Graphics : A Primer , 1994 .

[27]  I. Chouvarda,et al.  Indicators of Sleepiness in an ambulatory EEG study of night driving , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  Aluísio J. D. Barros,et al.  Acidentes de trânsito no Brasil de 1998 a 2010: muitas mudanças e poucos resultados , 2011 .

[29]  Björn Peters,et al.  Driver fatigue detection from electroencephalogram spectrum after electrooculography artefact removal , 2013 .

[30]  A. Barros,et al.  Traffic accidents in Brazil from 1998 to 2010: many changes and few effects. , 2011, Revista de saude publica.

[31]  Vernon J. Lawhern,et al.  Detecting alpha spindle events in EEG time series using adaptive autoregressive models , 2013, BMC Neuroscience.

[32]  Bruce P. Hunn.  The Use of EEG as a Workload Assessment Tool in Flight Test , 1993 .

[33]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[34]  Katarzyna Blinowska,et al.  ELECTROENCEPHALOGRAPHY (EEG) , 2006 .

[35]  Jean-Michel Poggi,et al.  Wavelet Toolbox User s Guide , 1996 .