A probabilistic real-time algorithm for detecting blinks, saccades, and fixations from EOG data

We present a computationally light real-time algorithm which automatically detects blinks, saccades, and fixations from electro-oculography (EOG) data and calculates their temporal parameters. The method is probabilistic which allows to consider the uncertainties in the detected events. The method is real-time in the sense that it processes the data sample-by-sample, without a need to process the whole data as a batch. Prior to the actual measurements, a short, unsupervised training period is required. The parameters of the Gaussian likelihoods are learnt using an expectation maximization algorithm. The results show the promise of the method in detecting blinks, saccades, and fixations, with detection rates close to 100 %. The presented method is published as an open source tool.

[1]  Ralf Engbert,et al.  Microsaccades are triggered by low retinal image slip. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[2]  F. Behrens,et al.  An improved algorithm for automatic detection of saccades in eye movement data and for calculating saccade parameters , 2010, Behavior research methods.

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

[4]  A. Chesson,et al.  The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications , 2007 .

[5]  Pekka-Henrik Niemenlehto,et al.  Constant false alarm rate detection of saccadic eye movements in electro-oculography , 2009, Comput. Methods Programs Biomed..

[6]  A. Fuchs,et al.  Further properties of the human saccadic system: eye movements and correction saccades with and without visual fixation points. , 1969, Vision research.

[7]  Mélodie Vidal,et al.  Analysing EOG signal features for the discrimination of eye movements with wearable devices , 2011, PETMEI '11.

[8]  J. Veltman,et al.  Physiological indices of workload in a simulated flight task , 1996, Biological Psychology.

[9]  Tomasz Przybyła,et al.  Fuzzy clustering based methods for nystagmus movements detection in electronystagmography signal , 2013 .

[10]  L Stark,et al.  Oblique saccadic eye movements. Independence of horizontal and vertical channels. , 1977, Archives of ophthalmology.

[11]  Ralf Engbert,et al.  Microsaccades uncover the orientation of covert attention , 2003, Vision Research.

[12]  Kilseop Ryu,et al.  Evaluation of mental workload with a combined measure based on physiological indices during a dual task of tracking and mental arithmetic , 2005 .

[13]  Terry A. Bahill,et al.  Variability and development of a normative data base for saccadic eye movements. , 1981, Investigative ophthalmology & visual science.

[14]  J. C. Miller,et al.  Electrooculographic and performance indices of fatigue during simulated flight , 1996, Biological Psychology.

[15]  T. Åkerstedt,et al.  Subjective sleepiness, simulated driving performance and blink duration: examining individual differences , 2006, Journal of sleep research.

[16]  Gerhard Tröster,et al.  Eye Movement Analysis for Activity Recognition Using Electrooculography , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  K. Müller,et al.  Automatic sleep stage classification using two-channel electro-oculography , 2007, Journal of Neuroscience Methods.

[18]  Kati Pettersson,et al.  Algorithm for automatic analysis of electro-oculographic data , 2013, BioMedical Engineering OnLine.

[19]  Bruno Jammes,et al.  Automatic EOG analysis: A first step toward automatic drowsiness scoring during wake-sleep transitions , 2008 .

[20]  Ralf Engbert,et al.  Microsaccades Keep the Eyes' Balance During Fixation , 2004, Psychological science.

[21]  Lance M. Optican,et al.  Saccade detection using a particle filter , 2014, Journal of Neuroscience Methods.

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

[23]  P. Caffier,et al.  Experimental evaluation of eye-blink parameters as a drowsiness measure , 2003, European Journal of Applied Physiology.

[24]  N G Henriksson,et al.  Effect of filtering in the computer analysis of saccades. , 1984, Acta oto-laryngologica. Supplementum.

[25]  W. Becker,et al.  Human oblique saccades: Quantitative analysis of the relation between horizontal and vertical components , 1990, Vision Research.

[26]  Tomasz Przybyła,et al.  An automatic saccadic eye movement detection in an optokinetic nystagmus signal , 2014, Biomedizinische Technik. Biomedical engineering.

[27]  Kenneth Holmqvist,et al.  Eye tracking: a comprehensive guide to methods and measures , 2011 .

[28]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[29]  J. Stern,et al.  The endogenous eyeblink. , 1984, Psychophysiology.