“Dyslector” – Dyslexia Detection
The software assesses the presence and degree of dyslexia in a school student based on gender, age, school grade and eye-tracking data using a pre-trained machine learning model
About the software system
Cross-platform solution
Works on desktop computers with Windows and MacOS operating systems, mobile version supports Android and iOS
Machine learning model
Contains a built-in pre-trained model (multi-layer percepton)
Functionality for detecting the presence and degree of dyslexia
Determines one of three classes - Normal, Dyslexia, Risk of dyslexia
Who's interested?
Psychologists, speech therapists and doctors will be able to use a machine learning model to diagnose dyslexia based on eye-tracking behavior
Advantages
Intuitive user interface
Mobile App available
No Data Scientist required
Programme authors
Olga Dragoy
Director of the Centre for Language and Brain, head of project “Experimental methods for assessing the quality of products of AI systems (evaluation of text generation models)” and “Diagnostic and assistive speech technologies based on artificial intelligence”
Soroosh Shalileh
Research Fellow at the Center for Language and Brain, head of the Vision Modelling Laboratory
Yury Zontov
Senior Lecturer at the School of Applied Mathematics, programmer at the Center for Language and Brain, junior Research Fellow at the International Centre of Decision Choice and Analysis