Prediction of Attention Deficit Hyperactivity Disorder (ADHD) using machine learning Techniques based on classification of EEG signal

The paper shows a comprehensive study of prediction of Attention Deficit Hyperactivity Disorder (ADHD) using machine learning in adults and children's and symptoms' of ADHD are hyperactivity, disruptive behavior and less attention. We analysis the classification performance of three algorithms of machine learning (Naïve Bayes, kNN, Logistic regression) applied on the dataset (of 157 children out of which 77 were ADHD patient and 80 were healthy) collected from open source. The Three Machine learning classifier range from simple (logistic regression) to advance (Naïve bayes). All three algorithms were applied on a dataset (157 students). The k nearest neighbor classifier is able to predict with high accuracy of 86% and it is far better than Naïve bayes (52%) and logistic regression (66 %). We report that k nearest neighbor classifier is able to attention deficit hyperactivity disorder with accuracy of 89%.