Detection of Dyslexia Using Eye Tracking

The goal of this paper is to provide another perspective and to extend the experiments conducted in Sweden in the article Screening for Dyslexia Using Eye Tracking during Reading. Our experiments were accomplished on a dataset containing 185 recordings of participants that was provided by previous r...

Full description

Saved in:
Bibliographic Details
Published in2021 Signal Processing Symposium (SPSympo) pp. 202 - 205
Main Authors Nerusil, Boris, Polec, Jaroslav, Skunda, Juraj
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.09.2021
Subjects
convolution neural network
dyslexia
Education
eye tracking
Gaze tracking
interpolation
Medical treatment
Pediatrics
Reliability
Signal processing
spectrum
Tracking
Online AccessGet full text

Cover

More Information
Summary:The goal of this paper is to provide another perspective and to extend the experiments conducted in Sweden in the article Screening for Dyslexia Using Eye Tracking during Reading. Our experiments were accomplished on a dataset containing 185 recordings of participants that was provided by previous researchers. Participants were categorized into two groups - High Risk (HR) and Low Risk (LR). 97 subjects (76 males and 21 females) were assigned to the HR group and 88 subjects (69 males and 19 females) were identified without dyslexia belonging to the LR group. Early detection of subjects suffering from cognitive impairment is beneficial in order to undergo therapy at an early stage and therefore the experiments were conducted on subjects attending the third grade of primary school (9 to 10 years old). Our approach achieved an accuracy score of 96.2 % (STD ±3.2) by classifying subjects into the correct groups.
DOI:10.1109/SPSympo51155.2020.9593313