Вісник № 02. Інформатика та моделювання

Переглянути

Зараз показуємо 1 - 1 з 1

Building a classifier in the personality recognition system based on eye tracking data
(Національний технічний університет "Харківський політехнічний інститут", 2021) Chori, V. V.; Shamanina, T. V.; Pavlenko, V. D.
The article proposes a new method of biometric identification of computer systems users, based on the determination of the integral Volterra model of the human oculo-motor system (OMS) according to experimental research "input-output" using innovative eye tracking technology. With the help of the Tobii Pro TX300 eye tracker, the data of OMC responses to test visual stimuli were obtained, displayed as bright dots on the computer screen at different distances from the start position in the "horizontal" direction. Based on the data obtained, the transition functions of the first, second and third orders of the OMS for two people were determined. To construct a personality classifier, the informativeness of the proposed heuristic features, determined on the basis of the transition functions in terms of the probability of correct recognition (PCR), is investigated. Pairs of features are established that are resistant to computational errors and have a high PCR value - in the range 0.92 - 0.97.