Attention Deficit Hyperactivity Disorder Using Machine Learning

High temporal resolution is provided by EEG signals, which is helpful for evaluating and diagnosing youngsters that suffer with ADHD. The goal of this research is to produce a model for ML for identifying youngsters with ADHD and healthy controls 60 youngsters having ADHD and 60 healthy controls provided EEG readings for this investigation who were doing cognitive activities were collected from an open-access database. Three classifiers—AdaBoost, ANN, and RF—used to identify and further test the regional contributions to achieving improved accuracy. 19 channels of EEG data are utilized as input characteristics for classifiers, both individually and in combinatorial groupings. When every channel is considered and the total performance of all the classifiers is evaluated, the Random Forest has the greatest accuracy (80.48%). This study demonstrates the distinct physiological differences between youngsters with ADHD an acronym for attention deficit hyperactivity disorder children who are typically growing and developing present in their brain activity and may to make a diagnosis.