Abstract: Attention deficit hyperactivity disorder (ADHD) is a standout amongst the most widely recognized disorder in school-age kids. To date, the determination of ADHD is for the most part subjective and investigations of target symptomatic strategy are of awesome significance. Although numerous endeavors have been made as of late to explore the use of structural and functional images of brain, for diagnosis, out of which a few are relevant for ADHD. Since the available dataset is unlabeled, we present a programmed grouping structure (k-means) to create clusters in view of MRI image of ADHD patients and normal subjects and present in detail highlight determination, and classifier preparing techniques. Classification algorithm K-Nearest Neighbor creates a classifier which classifies the input into the respective category.
Keywords: ADHD, s-MRI, f-MRI, Machine Learning, k-means, anamoly, random forest