Welcome to the InfoSci Platform
Reference Hub9
Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia

Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia

Jothi Prabha Appadurai, Bhargavi R.
Copyright: © 2021 |Volume: 15 |Issue: 4 |Pages: 22
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859857|DOI: 10.4018/IJCINI.20211001.oa28
Cite Article Cite Article

MLA

Appadurai, Jothi Prabha, and Bhargavi R. "Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia." IJCINI vol.15, no.4 2021: pp.1-22. http://doi.org/10.4018/IJCINI.20211001.oa28

APA

Appadurai, J. P. & Bhargavi R. (2021). Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(4), 1-22. http://doi.org/10.4018/IJCINI.20211001.oa28

Chicago

Appadurai, Jothi Prabha, and Bhargavi R. "Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.4: 1-22. http://doi.org/10.4018/IJCINI.20211001.oa28

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Dyslexia is a learning disorder that can cause difficulties in reading or writing. Dyslexia is not a visual problem but many dyslexics have impaired magnocellular system which causes poor eye control. Eye-trackers are used to track eye movements. This research work proposes a set of significant eye movement features that are used to build a predictive model for dyslexia. Fixation and saccade eye events are detected using the dispersion-threshold and velocity-threshold algorithms. Various machine learning models are experimented. Validation is done on 185 subjects using 10-fold cross-validation. Velocity based features gave high accuracy compared to statistical and dispersion features. Highest accuracy of 96% was achieved using the Hybrid Kernel Support Vector Machine- Particle Swarm Optimization model followed by the Xtreme Gradient Boosting model with an accuracy of 95%. The best set of features are the first fixation start time, average fixation saccade duration, the total number of fixations, total number of saccades and ratio between saccades and fixations.