Assessment of Bayesian Ternary Gaze Classification Algorithm (I-BDT) 14
I-BDT eyetracking data ternary classification (fixations, saccades, smooth pursuit) algorithm is investigated. Comparison with well-known Identification / Dispersion Threshold (I-DT) algorithm is held (accuracy, precision, recall, F1 measure). A novel approach for additionally filtering the algorithm output by distance/amplitude, area of convex hull is described.
Santini T., Fuhl W., Kübler T., et al. Bayesian
identification of fixations, saccades, and smooth pursuits. ACM ETRA.
Charleston, 2016. pp. 163–170. DOI:10.1145/2857491.2857512
Nyström M., Andersson R., Holmqvist K., et al. The
influence of calibration method and eye physiology on eyetracking data quality.
Behav. Res. Met. 2013. Vol. 45, no 1, pp. 272–288.
Hooge I., Holmqvist K., Nyström M. The pupil is faster
than the corneal reflection (CR): Are video based pupil-CR eye trackers
suitable for studying detailed dynamics of eye movements? Vis. Res.
2016. Vol. 128, pp. 6–18. DOI:10.1016/j.visres.2016.09.002.
Larsson L., Nyström M., Ardö H., et al. Smooth pursuit
detection in binocular eye-tracking data with automatic video-based performance
evaluation. J. Vis. 2016. Vol. 16, no 15, pp. 20.
Startsev M., Agtzidis I., Dorr M. 1D CNN with BLSTM for
automated classification of fixations, saccades, and smooth pursuits. Behav.
Res. Met. 2019. Vol. 51, pp. 556–572. DOI:10.3758/s13428–018–1144–2
Zemblys R., Niehorster D.C., Komogortsev O., et al. Using
machine learning to detect events in eye-tracking data. Behav. Res. Met.
2018. Vol. 50, pp. 160–181. DOI:10.3758/s13428–017–0860–3
Komogortsev O.V., Karpov A. Automated classification and
scoring of smooth pursuit eye movements in the presence of fixations and
saccades. Behav. Res. Met. 2013. Vol. 45, pp. 203–215.
Komogortsev O. V, Gobert D. V, Jayarathna S., et al.
Standartization of automated analyses of oculomotor fixation and saccadic
behaviors. IEEE Trans. Biomed. Eng. 2010. Vol. 57, no 11, pp. 2635–2645.
Kashyap H.J., Detorakis G., Dutt N., et al. A recurrent
neural network based model of predictive smooth pursuit eye movement in
primates. IEEE IJCNN. Rio de Janeiro, 2018. pp. 5353–5360.
Xivry J.J.O. de, Coppe S., Blohm G., et al. Kalman
Filtering Naturally Accounts for Visually Guided and Predictive Smooth Pursuit
Dynamics. J. Neurosci. 2013. Vol. 33, no 44, pp. 17301–17313.