Machine Learning and Dyslexia-Diagnostic and Classification System (DCS) for Kids with Learning Disabilities

• Main Authors: Rehman Ullah, Khan, Lee, Julia Ai Cheng, Oon, Yin Bee
• Format: Article
• Language: English
• Published: Science Publishing Corporation 2018
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://ir.unimas.my/id/eprint/21523/1/Rehman%20Ullah%20Khan.pdf; http://ir.unimas.my/id/eprint/21523/; https://www.sciencepubco.com/index.php/ijet/index

New generation is the future of every nation, but dyslexia which is a learning disability is spoiling the new generation. Most experts are using manual techniques to diagnose dyslexia. Machine learning algorithms are capable enough to learn the knowledge of experts and intelligently diagnose and classify dyslexics. This research proposes such a machine learning based diagnostic and classification system. The system is trained by human expert classified data of 857 school children scores in various tests. The data was collected in another fundamental research of designing special tests for dyslexics. Twenty-fifth percentile was used as threshold. The scores equal to the threshold and below were marked as indicators of children who were likely to have dyslexia while the scores above the threshold were considered to be indicators of children who were non-dyslexic. The system has three components: the diagnostic module is a pre-screening application that can be used by experts, trained users and parents for detecting the symptoms of dyslexia. The second module is classification, which classifies the kids into two groups, non-dyslexics and suspicious for dyslexia. A third module is an analysis tool for researchers. The results show that 20.7% of students seem to be dyslexic out of 257 in the testing data set which has confirmed by human expert.