Spatiotemporal Eye-Tracking Feature Set for Improved Recognition of Dyslexic Reading Patterns in Children

Abstract

Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification.

Vision-Based Eye Image Classification for Ophthalmic Measurement Systems

“…As a consequence, a score of would be obtained even with if the SFPT is not small enough ( ms). Moreover, the accuracy target score is set to 0.8 to limit, in the first place, the amount of wrongly discarded images to ( or ), and secondly, to match the minimum average score of algorithms with a similar task [ 32 , 44 , 83 ].In the equation, A is squared, such as any solutions, even with the lowest , will give a if the algorithm accuracy is lower than ( ). Figure 8 shows how the FOM from Equation ( 2 ) varies for different values of A and SFPT .…”

“…According to the research conducted by Winkler et al [ 28 ], the bulk of eye-tracking datasets gathered between 2004 and 2012 had an average viewing distance of 70 cm, with frames recorded in a laboratory environment using a chin rest, a biting bar, or head-mounted devices to limit the patients head movement. Other datasets, instead, include face and eyes images collected in natural environments [ 29 ] or with commercially available devices, such as smartphones [ 30 ], thus to solve most common eye gaze estimation during everyday tasks, such as driving [ 31 ], reading [ 32 ], or browsing the internet [ 33 ]. Other studies include images for the detection of natural blinks [ 34 , 35 ], some of them with the aim of improving gaze estimation [ 36 ].…”

Eye-Tracking Image Encoding: Autoencoders for the Crossing of Language Boundaries in Developmental Dyslexia Detection

“…An in-depth analysis of the gathered eye-tracking data was performed in a later study and included an introduction of new eye-tracking features [26]. The novel features, focusing on the spatial characteristics of fixations, were compared to the conventional eye-tracking features and have shown superior results in dyslexia classification.…”

“…These images were then used to train and evaluate a deep twodimensional CNN. The goal of the study was to use the same aspect of dyslexic tendencies as in [26] but to rely on the powerful pattern recognition capabilities of the CNN and an image representation of eye-tracking data.…”

“…Based on the spatial complexity principle in the method published in the author's previous study [26], this paper focuses on making the quantification of spatial complexity more universal. The eye movements do not have to be segmented into fixations and saccades in order to apply the algorithm presented in this paper.…”