Predicting Gender via Eye Movements

In this paper, we report the first stable results on gender prediction via eye movements. We use a dataset with images of faces as stimuli and with a large number of 370 participants. Stability has two meanings for us: first that we are able to estimate the standard deviation (SD) of a single prediction experiment (it is around 4.1 %); this is achieved by varying the number of participants. And second, we are able to provide a mean accuracy with a very low standard error (SEM): our accuracy is 65.2 %, and the SEM is 0.80 %; this is achieved through many runs of randomly selecting training and test sets for the prediction. Our study shows that two particular classifiers achieve the best accuracies: Random Forests and Logistic Regression. Our results reconfirm previous findings that females are more biased towards the left eyes of the stimuli.

An Extensive Study of User Identification via Eye Movements across Multiple Datasets

Several studies have reported that biometric identification based on eye movement characteristics can be used for authentication. This paper provides an extensive study of user identification via eye movements across multiple datasets based on an improved version of method originally proposed by George and Routray. We analyzed our method with respect to several factors that affect the identification accuracy, such as the type of stimulus, the IVT parameters (used for segmenting the trajectories into fixation and saccades), adding new features such as higher-order derivatives of eye movements, the inclusion of blink information, template aging, age and gender.We find that three methods namely selecting optimal IVT parameters, adding higher-order derivatives features and including an additional blink classifier have a positive impact on the identification accuracy. The improvements range from a few percentage points, up to an impressive 9 % increase on one of the datasets.