Applying Bagging Machine Learning Techniques to Diagnose Dyslexia in Visual Tasks

Dyslexia is a disorder of neurological origin that primarily impacts children's learning, resulting in difficulties with reading and writing. If left undiagnosed, it can cause significant frustration and feelings of intimidation for both the affected children and their families. Without early intervention, these children may experience substantial academic achievement gaps by the time they reach high school. Early detection and intervention for dyslexic students are crucial for fostering positive self-esteem and maximizing academic potential. This paper introduces a Bagging approach for automatically identifying dyslexia in children using machine learning techniques. In this study, we pre-processed brain signals and extracted EEG signal features across 19 channels, focusing on the amplitude and latency of ERP components. Due to the high number of features, we employed Principal Component Analysis (PCA) for feature reduction. To prevent overfitting, we utilized K-fold cross-validation and ultimately, we applied the bagging method for classification.Using this approach, we achieved an overall average classification accuracy of 90.6%, with sensitivity and specificity rates of 100% and 81.2%, respectively

Applying Bagging Machine Learning Techniques to Diagnose Dyslexia in Visual Tasks Keywords:

_Dyslexia , Electroencephalography (EEG) , Ensemble Learning , Machine Learning , Event-Related Potential (ERP)_