Development of a Multiple RGB-D Sensor System for ADHD Screening and Improvement of Classification Performance Using Feature Selection Method

Attention deficit and hyperactivity disorder (ADHD) is a mixed behavioral that exhibits symptoms, such as carelessness hyperactivity–impulsivity. To date, existing ADHD diagnosis methods rely on observations by observers, parents teachers, which limits the ability to reflect objective evaluation. In this study, overcome limitation, we proposed multiple RGB-D sensor system can objectively measure amount of action attention children playing robot-led game. addition, classifier was developed classify into ADHD, risk, normal groups using multilayer perceptron data obtained through sensors. The effectiveness for screening verified. priority abnormal behavior indicators designed measured, features with highest were selected feature selection method. Eight hundred twenty-eight participated classified groups, results compared clinicians. achieved sensitivity 97.06% 100%, specificity 96.42% 94.68% in risk respectively.