AI-Driven Personalized Learning Framework for Students with Neurological Disorders: A Deep Learning Approach

Abstract

AI-Driven Personalized Learning Framework for Students with Neurological Disorders is an intelligent educational framework which can adjust learning content based on the cognitive behavior, attention variability and emotional engagement pattern of students with neurological disorders. The proposed framework, NeuroLearn-DL is composed of Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) algorithm for analysing and recommending personalized content based on multimodal behavior. The framework was tested with the publicly available dataset Autism Spectrum Disorder Screening from UCI Machine Learning Repository along with some of the features for the interaction of the learners. To enhance the accuracy of the educational response prediction, some data preprocessing methods like summarizing content, normalizing features, tracking attention, and modeling adaptable recommendations were adopted.Some data preprocessing methods such as summarizing content, normalizing features, tracking attention, and modeling adaptable recommendations were used to improve the accuracy of educational response prediction. The experimental results showed that it achieved an accuracy of 97.2%, precision of 96.4%, recall of 95.8%, and F1 score of 96.1%, which improved the classification accuracy by 11.6% compared with the conventional machine learning methods. The proposed framework provides an adaptive learning mechanism with real-time functionality that adopts the cognitive analytics, behavioral monitoring, and deep personalized recommendations strategy. The study shows that deep learning personalized education has the potential to greatly improve students' engagement in learning, efficiency of understanding and ease of study for students with neurological disorders. The framework also contributes to the retention, inclusion and lifelong cognitive growth of children.