Empirical Development of Metaheuristic and Deep Learning Models for Early Prediction of Dyslexia in Children

Abstract

Dyslexia is a precise learning disability which is a neurobiological disorder with newlinea plausible genetic origin. Approximately 10% of the global population is affected by this newlinetype of learning disability. Children with dyslexia are at the hazard of deprived self-esteem newlineand when they see their peers reading confidentiality, they may develop a negative selfconcept newlinewhich results in depression. Research on dyslexia shows that early identification is newlinecritical since 85% of brain development occurs by the age of five and there are very few newlinetreatments available for very young children who struggle with their learning. Detecting newlinedyslexia among children in earlier stages and providing them special assistance in education newlineoften enhance their learning and reading skills enough to succeed in grade school. Dyslexia newlineis not a disease but it is a lifelong condition, which can be tackled with specialist teaching newlinetechniques and the use of specialized strategies. newlineThe ultimate goal of this research work is to design and develop three different newlinemethodologies for early detection of dyslexia among school children which assist the experts newlineto overwhelm their difficulties in reading and learning skills more precisely. The newlinedyslexic_12_4 dataset, which is derived from the Knowledge Extraction based on newlineEvolutionary Learning (KEEL) dataset, is gathered for this procedure newline