Building a classifier in the personality recognition system based on eye tracking data

Identification systems that use biometric characteristics to solve the problem of access information are becoming more common. The article proposes a new method identification computer users, based on determination integral Volterra model human oculo-motor system (OMS) according experimental research "input-output" using innovative eye tracking technology. With help Tobii Pro TX300 tracker, data OMC responses test visual stimuli were obtained, displayed as bright dots screen at different distances from start position in "horizontal" direction. Based transition functions first, second and third orders OMS for two people determined. To construct personality classifier, informativeness proposed heuristic features, determined basis terms probability correct recognition (PCR), is investigated. Pairs features established resistant computational errors have high PCR value - range 0.92 0.97. Fig.: 8. Table: 5. Bibliography: 30 items.
 Key words: identification, recognition, model, system, technology, classification.