September 26, 2012
New Technology Allows For Closer Study Of Autism In Children
Connie K. Ho for redOrbit.com — Your Universe Online
People have said that the eyes are the windows to the soul. Students of public speaking are encouraged to make contact, while Western businessmen utilize eye contact to signify that attention is given to the speaker. Reluctance in frequent or prolonged eye contact is also a sign of autism. Researchers have wanted to develop systems that could measure eye contact and other telltale signs of problem behaviors in autism. Recently, scientists from Georgia Tech´s Center for Behavior Imaging (CBI) revealed that they have been able to develop new tech tools that can track the relevant behaviors of children, which can be utilized in research on behavioral disorders like autism.
“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,” remarked the study´s principal investigator Jim Rehg, CBI director and professor in Georgia Tech´s School of Interactive Computing, in a prepared statement. “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. We call these results preliminary because they were obtained from a single subject, but all humans´ eyes work pretty much the same way, so we´re confident the successful results will be replicated with future subjects.”
With the eye-contact tracking system, individuals wear a pair of glasses that can track the focal point of the wearer. Researchers were able to record a video of a child with a camera placed on the front of a pair of lenses worn by an adult who was interacting with the child. Facial recognition software then processed the video and allowed the researchers to detect whether there was eye contact between the two individuals. Tests were conducted in Georgia Tech´s Child Study Lab (CSL) and scientists believe that the system has 80 percent accuracy.
“These results are very promising in leading the way toward more accurate and reliable measurement of problem behavior, which is important in determining whether treatments targeting these behaviors are working,” commented CSL Director Agata Rozga, a research scientist in the School of Interactive Computing, in the statement. “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. 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 that they can address them immediately.”
The other tool, developed collaboratively with the Marcus Autism Center and Dr. Thomas Ploetz of Newcastle University in the United Kingdom, featured a package of sensors that can be worn as straps on the wrists and ankles to measure movement by the wearer. The scientists developed a set of algorithms that can study the sensor data to recognize situations with problem behavior, categorizing them as “aggressive, self-injurious, or disruptive.”
“What these tools show is that computational methods and technologies have great promise and potential impact on the lives of many children and their parents and caregivers,” concluded Gregory Abowd, Regents´ Professor in the School of Interactive Computing at Georgia Tech who studies technology and autism, in the statement. “These technologies we are developing, and others developed and explored elsewhere, aim to bring more effective early-childhood screening to millions of children nationwide, as well as enhance care for those children already diagnosed on the autism spectrum.”