scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Prediction of Dyslexia from Eye Movements Using Machine Learning

12 Jun 2019-Iete Journal of Research (Informa UK Limited)-pp 1-10
TL;DR: Dyslexia is a reading disability and a language disorder where the individual exhibits difficulty in reading, writing, speaking, and trouble in spelling words.
Abstract: Dyslexia is a reading disability and a language disorder where the individual exhibits difficulty in reading, writing, speaking, and trouble in spelling words. Early prediction of dyslexia can help...
Citations
More filters
Journal ArticleDOI
TL;DR: In this article, a review of state-of-the-art machine learning methods for dyslexia and its biomarkers is presented, where the authors discuss challenges that require proper attentions from the users of deep learning methods in order to attain clinically relevance and acceptable level.
Abstract: Dyslexia is a neurological disorder that is characterized by imprecise comprehension of words and generally poor reading performance. It affects a significant population of school-age children, with more occurrences in males, thus, putting them at risk of poor academic performance and low self-esteem for a lifetime. The long-term hope is to have a dyslexia diagnostic method that is informed by neural-biomarkers. In this regard, large numbers of machine learning methods and, more recently, deep learning methods have been implemented across various types of dataset with the above-chance classification accuracy. However, attainment of clinical acceptability of these state-of-the-art methods is bedeviled by certain challenges including lack of biologically-interpretable biomarkers, privacy of dataset and classifiers, hyper-parameter selection/optimization, and overfitting problem among others. This review paper critically analyzes recent machine learning methods for detecting dyslexia and its biomarkers and discusses challenges that require proper attentions from the users of deep learning methods in order to enable them to attain clinically relevance and acceptable level. The review is conducted within the premise of implementation and experimental outcomes for each of the 22 selected articles using the Preferred Reporting Items for Systematic review and Meta-Analyses (PRISMA) protocol, with a view to outlining some critical challenges for achieving high accuracy and reliability of the state-of-the-art machine learning methods. As an evidence-based protocol for reporting in systematic reviews and meta-analyses, PRISMA helps to ensure clarity and transparency of this paper by showing a four-phase flow diagram of the selection process for articles used in this review. It is therefore, envisaged that higher classification performance of clinical relevance can be achieved using deep learning models for dyslexia and its biomarkers by addressing identified potential challenges.

34 citations

Journal ArticleDOI
01 Dec 2021
TL;DR: This work establishes groundwork for automatic detection of dyslexia in a natural reading situation by using machine learning methods to identify individuals with low performance of reading fluency using their eye movement recordings of reading.
Abstract: Dyslexia is a common neurocognitive learning disorder that can seriously hinder individuals’ aspirations if not detected and treated early. Instead of costly diagnostic assessment made by experts, in the near future dyslexia might be identified with ease by automated analysis of eye movements during reading provided by embedded eye tracking technology. However, the diagnostic machine learning methods need to be optimized first. Previous studies with machine learning have been quite successful in identifying dyslexic readers, however, using contrasting groups with large performance differences between diagnosed and good readers. A practical challenge is to identify also individuals with borderline skills. Here, machine learning methods were used to identify individuals with low performance of reading fluency (below 10 percentile from a normal distribution) using their eye movement recordings of reading. Random Forest was used to select most important eye movement features to be used as input to a Support Vector Machine classifier. This hybrid method was capable of reliably identifying dysfluent readers and it also provided insight into the data used. Our best model achieved accuracy of 89.7% with recall of 84.8%. Our results thus establish groundwork for automatic detection of dyslexia in a natural reading situation.

22 citations

Journal ArticleDOI
TL;DR: A small set of eye movement features have been proposed that contribute more to distinguish between dyslexics and non-dyslexics by machine learning models that performed better than those detected by dispersion-based algorithms and statistical measures.

21 citations

Proceedings ArticleDOI
01 Aug 2020
TL;DR: A model is developed to reduce the existing challenges of eye-tracking studies and which machine algorithm would give the best result, with its applications, and a brief description of the eye movement metrics is given.
Abstract: Eye-tracking studies in software engineering are becoming more prevalent and also in the areas like medical, gaming and commercial fields. Researchers may use the same metrics but it is majorly used to give a different name for same field that cause the difficulties in comparing studies, so in this work, a model is developed to reduce the existing challenges. Many existing algorithms are available to apply on eye tracking data but machine learning is one of the best algorithms, for example random forest is one the machine learning algorithms, which helps to hold the test set. In the eye movement metrics, the dataset will be divided into two sets they are: test set and training set. This paper reports on the eye-tracking metries using raw eye-tracking data. The proposed research work has used random forest, decision tree, KNN and SVM for experimentation in order to understand the dataset. The objective of this study is two-fold. First, the identification of various eye movement metrics events and Second, Apply visualization technique. It can be applied in medical field. Here first we will identify the accuracy, recall, precision and f-measure between KNN classifier and SVM, then identifying the eye movement metrics using machine learning algorithm. We give in this research a brief description of the eye movement metrics and which machine algorithm would give the best result, with its applications.

13 citations

Journal ArticleDOI
TL;DR: In this article , an adaptive reinforcement learning framework known as RALF through Cellular Learning Automata (CLA) was introduced to generate content automatically for students with dyslexia, which is a learning disorder in which individuals have significant reading difficulties.
Abstract: Dyslexia is a learning disorder in which individuals have significant reading difficulties. Previous studies found that using machine learning techniques in content supplements is vital in adapting the course concepts to the learners' educational level. However, to the best of our knowledge, no research objectively applied machine learning methods to adaptive content generation. This study introduces an adaptive reinforcement learning framework known as RALF through Cellular Learning Automata (CLA) to generate content automatically for students with dyslexia. At first, RALF generates online alphabet models as a simplified font. CLA structure learns each rule of character generation through the reinforcement learning cycle asynchronously. Second, Persian words are generated algorithmically. This process also considers each character's state to decide the alphabet cursiveness and the cells' response to the environment. Finally, RALF can generate long texts and sentences using the embedded word-formation algorithm. The spaces between words are proceeds through the CLA neighboring states. Besides, RALF provides word pronunciation and several exams and games to improve the learning performance of people with dyslexia. The proposed reinforcement learning tool enhances students' learning rate with dyslexia by almost 27% compared to the face-to-face approach. The findings of this research show the applicability of this approach in dyslexia treatment during Lockdown of COVID-19.

9 citations

References
More filters
Journal ArticleDOI
TL;DR: The basic ideas of PCA are introduced, discussing what it can and cannot do, and some variants of the technique have been developed that are tailored to various different data types and structures.
Abstract: Large datasets are increasingly common and are often difficult to interpret. Principal component analysis (PCA) is a technique for reducing the dimensionality of such datasets, increasing interpretability but at the same time minimizing information loss. It does so by creating new uncorrelated variables that successively maximize variance. Finding such new variables, the principal components, reduces to solving an eigenvalue/eigenvector problem, and the new variables are defined by the dataset at hand, not a priori , hence making PCA an adaptive data analysis technique. It is adaptive in another sense too, since variants of the technique have been developed that are tailored to various different data types and structures. This article will begin by introducing the basic ideas of PCA, discussing what it can and cannot do. It will then describe some variants of PCA and their application.

4,289 citations

Journal ArticleDOI
TL;DR: The evidence presented here will demonstrate that the system of eyeball and orbital tissues is heavily overdamped, has no resonant frequency and is little affected by the mass of the eyeball.
Abstract: In the investigation of oculomotor systems and especially in the mathematical descriptions of them as pursuit, tracking and stabilizing systems, the need arises for a more exact knowledge of the mechanics of the eyeball, the extraocular muscles and the supporting tissues of the orbit, particularly of the way in which these factors permit the globe to respond to the efferent discharges arising in the oculomotor nuclei. In 1954 Westheimer proposed that the eye moved in a saccade by the application of a step function of net muscular force. He further proposed that the mechanical system was of second order, slightly underdamped and had a natural resonant frequency of about 120 radians per second (19 c/s). Alpern (1962) has discussed the inadequacy of this picture in view of the large burst of activity during a saccade recorded by extraocular electromyography (Bj6rk, 1955; Miller, 1958). The development of the suction contact lens has made practicable a closer investigation of the mechanics of the saccade, for it provides a simple method of applying known forces and loads to the eye while measuring subsequent rotations without fear of lens slippage. The evidence presented here will demonstrate that the system of eyeball and orbital tissues is heavily overdamped, has no resonant frequency and is little affected by the mass of the eyeball. It has an upper mechanical frequency response of only 1 c/s and it succeeds in making quick saccadic movements only under the impetus of a large, briefly applied, excess force delivered by the extraocular muscles. For example, in maintaining the eye 100 horizontally from the primary position the horizontal recti need apply a net force of only 15 g but during the saccade to reach that position they apply about 43 g during the first 40 msec of movement.

888 citations

Journal ArticleDOI
TL;DR: Eyetracking measures provide non-invasive and rich indices of brain function and cognition and gaze analysis reveals current attentional focus and cognitive strategies.

412 citations

Journal ArticleDOI
06 Dec 2013-Science
TL;DR: It is found that phonetic representations are hosted bilaterally in primary and secondary auditory cortices and that their neural quality (in terms of robustness and distinctness) is intact in adults with dyslexia and that the functional and structural connectivity between the bilateral auditory cortice and the left inferior frontal gyrus is significantly hampered in dyslexics, suggesting deficient access to otherwise intact phonetic representation.
Abstract: Dyslexia is a severe and persistent reading and spelling disorder caused by impairment in the ability to manipulate speech sounds. We combined functional magnetic resonance brain imaging with multivoxel pattern analysis and functional and structural connectivity analysis in an effort to disentangle whether dyslexics’ phonological deficits are caused by poor quality of the phonetic representations or by difficulties in accessing intact phonetic representations. We found that phonetic representations are hosted bilaterally in primary and secondary auditory cortices and that their neural quality (in terms of robustness and distinctness) is intact in adults with dyslexia. However, the functional and structural connectivity between the bilateral auditory cortices and the left inferior frontal gyrus (a region involved in higher-level phonological processing) is significantly hampered in dyslexics, suggesting deficient access to otherwise intact phonetic representations.

361 citations

Journal ArticleDOI
TL;DR: This paper presents a literature survey on the PSO algorithm and its variants to clustering high-dimensional data and an attempt is made to provide a guide for the researchers who are working in the area of PSO and high- dimensional data clustering.
Abstract: Data clustering is one of the most popular techniques in data mining. It is a process of partitioning an unlabeled dataset into groups, where each group contains objects which are similar to each other with respect to a certain similarity measure and different from those of other groups. Clustering high-dimensional data is the cluster analysis of data which have anywhere from a few dozen to many thousands of dimensions. Such high-dimensional data spaces are often encountered in areas such as medicine, bioinformatics, biology, recommendation systems and the clustering of text documents. Many algorithms for large data sets have been proposed in the literature using different techniques. However, conventional algorithms have some shortcomings such as the slowness of their convergence and their sensitivity to initialization values. Particle Swarm Optimization (PSO) is a population-based globalized search algorithm that uses the principles of the social behavior of swarms. PSO produces better results in complicated and multi-peak problems. This paper presents a literature survey on the PSO algorithm and its variants to clustering high-dimensional data. An attempt is made to provide a guide for the researchers who are working in the area of PSO and high-dimensional data clustering.

267 citations