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.
Highlights
Dyslexia is a kind of neurodevelopmental deficit that causes persistent difficulties in reading and writing
Three types of features such as statistical, dispersion and velocity based are generated from the raw eye gaze data. For these 3 different sets of features generated, a significant set of features are selected by using feature selection algorithms Principal Component Analysis (PCA) and Recursive feature Elimination with Cross-Validation (RFE-CV)
It has been observed that Xtreme Gradient Boosting algorithm (XGBoost) and Hybrid Kernel Support Vector Machine (SVM)-Particle Swarm Optimization (PSO) classifiers gave better predictive accuracy compared to other models
Summary
Dyslexia is a kind of neurodevelopmental deficit that causes persistent difficulties in reading and writing. Dyslexics have poor information processing skills causing short term memory loss while reading (Karande & Agarwal, 2017). Eye trackers are used for detecting gaze points during eye movements In linguistic studies, they are used to identify saccades, fixations, smooth pursuit eye movements. The reading process has two types of eye movement events fixations and saccades that occur alternatively. Eye movement events give us information such as the time spent by the reader on a particular word or a line, thereby helping us to know their reading pattern (Wang & Ren, 2019). Exploring and identifying a set of significant features of saccades and fixations along with machine learning algorithms help us in the early prediction of dyslexia. This paper analyzes and identifies a set of eye movement features that contribute more to the prediction of dyslexia using machine learning algorithms.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
