Outlier-Aware, density-Based gaze fixation identification

Abstract Eye tracking is an advancing technology holding significant promise to improve our understanding of human behavior and decision making. Gaze data gathered by eye trackers contain events known as fixations. Fixations indicate visual attention and awareness, and are identified by algorithms that parse eye-tracking data into a sequence of gaze point clusters. While great potential exists, eye-tracker imprecision often results in noisy gaze data, such as what arises from calibration errors, erratic eye movements, or other system noise. Noise can cause inaccurate identification of fixations in eye-tracking applications, resulting in misleading behavioral interpretations and conclusions. Therefore, fixation identification algorithms should be robust against data noise. To resolve such inaccuracies, we propose FID + : outlier-aware fixation identification via fixation inner-density. We represent the problem of detecting outliers in fixation gaze data through a novel mixed-integer optimization formulation, and subsequently strengthen the formulation using two geometric arguments to provide enhanced bounds. We show that neither bound dominates the other, and that both are effective in reducing the overall solution runtime. Our experiments on real gaze recordings demonstrate that accommodating for the reality of fixation outliers enhances the ability to identify fixations with greater density in reasonable runtime.

[1]  Teresa Iacono,et al.  A systematic review of research into aided AAC to increase social-communication functions in children with autism spectrum disorder , 2017, Augmentative and alternative communication.

[2]  Shawn Plesnick,et al.  Eye-controlled wheelchair , 2014, 2014 IEEE Canada International Humanitarian Technology Conference - (IHTC).

[3]  Andreas Bulling,et al.  Wearable eye tracking for mental health monitoring , 2012, Comput. Commun..

[4]  J RousseeuwPeter,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[5]  M. Clarke,et al.  Augmentative and alternative communication for children with cerebral palsy , 2012 .

[6]  Martin Meißner,et al.  Eye Tracking Reveals Processes that Enable Conjoint Choices to Become Increasingly Efficient with Practice , 2016 .

[7]  P. Blignaut.  Fixation identification: The optimum threshold for a dispersion algorithm , 2009, Attention, perception & psychophysics.

[8]  Jacob L. Orquin,et al.  Eye Tracking and Nutrition Label Use: A Review of the Literature and Recommendations for Label Enhancement , 2012 .

[9]  Arthur Zimek,et al.  On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study , 2016, Data Mining and Knowledge Discovery.

[10]  Joseph H. Goldberg,et al.  Identifying fixations and saccades in eye-tracking protocols , 2000, ETRA.

[11]  Wen Liu,et al.  Identifying Fixations in Gaze Data via Inner Density and Optimization , 2019, INFORMS J. Comput..

[12]  Simon Cooper,et al.  Eye tracking to investigate cue processing in medical decision-making: A scoping review , 2017, Computers in Human Behavior.

[13]  Marcus Nyström,et al.  One algorithm to rule them all? An evaluation and discussion of ten eye movement event-detection algorithms , 2016, Behavior Research Methods.

[14]  D. Robinson.  The mechanics of human smooth pursuit eye movement. , 1965, The Journal of physiology.

[15]  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.

[16]  Thomas S. Tullis,et al.  Generation Y, web design, and eye tracking , 2010, Int. J. Hum. Comput. Stud..

[17]  Katharina Scheiter,et al.  Eye tracking as a tool to study and enhance multimedia learning , 2010 .

[18]  Joseph H. Goldberg,et al.  Eye tracking in web search tasks: design implications , 2002, ETRA.

[19]  Marcus Nyström,et al.  Eye tracker data quality: what it is and how to measure it , 2012, ETRA.

[20]  Soussan Djamasbi,et al.  Density of Gaze Points Within a Fixation and Information Processing Behavior , 2016, HCI.

[21]  Oleg V. Komogortsev,et al.  Standardization of Automated Analyses of Oculomotor Fixation and Saccadic Behaviors , 2010, IEEE Transactions on Biomedical Engineering.

[22]  Charu C. Aggarwal,et al.  Outlier Detection for Temporal Data: A Survey , 2014, IEEE Transactions on Knowledge and Data Engineering.

[23]  Marcus Nyström,et al.  The influence of calibration method and eye physiology on eyetracking data quality , 2013, Behavior research methods.

[24]  Katrien van Driessen,et al.  A Fast Algorithm for the Minimum Covariance Determinant Estimator , 1999, Technometrics.

[25]  Heinrich Kuhn,et al.  Retail category management: State-of-the-art review of quantitative research and software applications in assortment and shelf space management , 2012 .

[26]  Michel Wedel,et al.  Defining eye-fixation sequences across individuals and tasks: the Binocular-Individual Threshold (BIT) algorithm , 2010, Behavior research methods.

[27]  Quan Wang,et al.  Modified DBSCAN algorithm on oculomotor fixation identification , 2016, ETRA.

[28]  Meredith Ringel Morris,et al.  Toward Everyday Gaze Input: Accuracy and Precision of Eye Tracking and Implications for Design , 2017, CHI.

[29]  A. Aldo Faisal,et al.  Towards free 3D end-point control for robotic-assisted human reaching using binocular eye tracking , 2017, 2017 International Conference on Rehabilitation Robotics (ICORR).

[30]  Zheru Chi,et al.  Strabismus Recognition Using Eye-Tracking Data and Convolutional Neural Networks , 2018, Journal of healthcare engineering.

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

[32]  P. Blignaut,et al.  Eye-tracking data quality as affected by ethnicity and experimental design , 2014, Behavior research methods.

[33]  Michiel Smid,et al.  Finding k points with a smallest enclosing square , 1993 .

[34]  Soussan Djamasbi,et al.  Eye Tracking and Web Experience , 2014 .

[35]  Giacomo Veneri,et al.  Automatic eye fixations identification based on analysis of variance and covariance , 2011, Pattern Recognition Letters.

[36]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[37]  Meredith Ringel Morris,et al.  Smartphone-Based Gaze Gesture Communication for People with Motor Disabilities , 2017, CHI.

[38]  Andrew T Duchowski,et al.  A breadth-first survey of eye-tracking applications , 2002, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[39]  Savannah Wei Shi,et al.  Information Acquisition During Online Decision Making: A Model-Based Exploration Using Eye-Tracking Data , 2013, Manag. Sci..

[40]  Sue Fletcher-Watson,et al.  Designing AAC Systems for Children with Autism: Evidence from Eye Tracking Research , 2014, Augmentative and alternative communication.

[41]  Maurizio Filippone,et al.  A comparative evaluation of outlier detection algorithms: Experiments and analyses , 2018, Pattern Recognit..

[42]  Marcus Nyström,et al.  An adaptive algorithm for fixation, saccade, and glissade detection in eyetracking data , 2010, Behavior research methods.

[43]  M. Y. Hu,et al.  A note on detecting outliers in short autocorrelated data using joint estimation and exponentially weighted moving average , 2003 .

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

[45]  Oleg V. Komogortsev,et al.  Eye movement prediction by oculomotor plant Kalman filter with brainstem control , 2009 .

[46]  Robin K. Morris,et al.  Processing Subject and Object Relative Clauses: Evidence from Eye Movements , 2002 .

[47]  Eric T. Bradlow,et al.  Does In-Store Marketing Work? Effects of the Number and Position of Shelf Facings on Brand Attention and Evaluation at the Point of Purchase , 2009 .

[48]  Wen Liu,et al.  Measuring Focused Attention Using Fixation Inner-Density , 2018, HCI.