Understanding autism behaviors is the goal behind new technologies being developed by researchers at the Georgia Institute of Technology. The researchers, working in the school's Center for Behavior Imaging, have created a system that uses special gaze-tracking glasses and facial-analysis software for eye-contact detection, as well as a wearable sensor system to help detect harmful "problem behaviors."
The software analyzed data from the eye-tracking device with 80 percent accuracy.
"Eye gaze has been a tricky thing to measure in laboratory settings, and typically it's very labor-intensive, involving hours and hours of looking at frames of video to pinpoint moments of eye contact," Jim Rehg, director at the Center for Behavior Imaging, said in an announcement. "The exciting thing about our method is that it can produce these same measures automatically and could be used in the future to measure eye contact outside the laboratory setting."
The wearable sensors use accelerometers that detect movement by subjects wearing straps on their wrists and ankles. Algorithms determine if their movements are normal or harmful. In tests of the strap technology on a child on the autism spectrum, the sensors were able to detect problem-behavior episodes with 81 percent accuracy, and classify 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, in settings where the child spends most of their time, such as their home or school," Agata Rozga, director of Georgia Tech's Child Study Lab, said in the announcement. "In this way, parents, teachers and others who care for the child can be potentially alerted to times and situations when problem behaviors occur so they can address them immediately."
In a similar project, researchers at the University of Minnesota currently are trying to use Microsoft Kinect sensors to aid autism diagnosis and care. Meanwhile, researchers at Harvard Medical School developed a publicly available online procedure that cuts diagnosis time from hours to minutes.
Tablet technology, meanwhile, is being used to help children diagnosed with autism develop better social skills.
To learn more:
- here's the Georgia Tech announcement