Georgia Tech researchers have developed two tools that automatically measure children's behavior to provide insight into behavioral disorders such as autism.
One system combines eye-tracking glasses and facial-recognition software to determine when children are making eye contact, and the other is a wearable system that uses accelerometers to monitor and categorize problem behaviors in children. Both technologies are being deployed in Georgia Tech's Center for Behavior Imaging, which is applying computational methods to screen, measure, and understand autism and other behavioral disorders.
"The exciting thing about our method is that it can produce these measures automatically and could be used in the future to measure eye contact outside the laboratory setting," says Georgia Tech professor Jim Rehg.
The wearable system consists of sensors that use accelerometers to detect movement by the user. Algorithms then analyze the sensor data to automatically detect episodes of problem behavior and classify them. During testing, the system was able to detect problem-behavior episodes with 81 percent accuracy and classified them with 70 percent accuracy.
"Our ultimate goal with this wearable sensing system is to be able to gather data on the child’s behavior beyond the clinic," says Georgia Tech researcher Agata Rozga.
From Georgia Tech News
View Full Article
No entries found