Automatic detection of stereotyped hand flapping movements: Two different approaches

Stereotypical motor movements are one of the most common and least understood behaviors occurring in individuals with Autism Spectrum Disorder (ASD). The traditional methods for recording the number of occurrences and duration of stereotypies are insufficient and time consuming. Thus the objective of this study is to automatically detect stereotypical motor movements in real time considering two different approaches. The first approach uses the Microsoft sensor Kinect and gesture recognition algorithms. The second approach uses a trademark device of Texas Instruments with built-in accelerometers and statistical methods to recognize stereotyped movements. The two proposed systems were tested in children with Autism Spectrum Disorders (ASD) and the results are compared. This study provides a valuable tool to monitor stereotypes in order to understand and to cope with this problematic. In the end, it facilitates the identification of relevant behavioral patterns when studying interaction skills in children with ASD.