Machine Learning Based Framework for Classification of Children with ADHD and Healthy Controls

• DOI: 10.32604/iasc.2021.017478
• Publication Date: 2021-04-22T07:44:56Z
• Authors: Anshu Parashar; Nidhi Kalra; Jaskirat Singh; Raman Kumar Goyal
• Keywords: AdaBoost

Electrophysiological (EEG) signals provide good temporal resolution and can be effectively used to assess diagnose children with Attention Deficit Hyperactivity Disorder (ADHD). This study aims develop a machine learning model classify ADHD Healthy Controls. In this study, EEG captured under cognitive tasks were obtained from an open-access database of 60 Controls similar age. The regional contributions towards attaining higher accuracy are identified further tested using three classifiers: AdaBoost, Random Forest Support Vector Machine. data 19 channels is taken as input features in individual combinatorial sets classifiers. Evaluating all the classifiers' overall performance, highest 84% AdaBoost classifier when Right Hemisphere into consideration. sensitivity 96% indicates better true positive detection rate created features. highlights intrinsic physiological contrast prevalent brain activity healthy children, which utilized for diagnostic purposes.