This article is in concert with last week’s about AI and children with autism. This topic is so important, I thought it warranted another look at what scientists have come up with.
(By the way. You can access the complete report about the Qtrobot at this link:
If you can’t get there by clicking on it, copy and paste it into the url bar and it will take you there.)
The incidences of autism is growing, so the Stanford University School of Medicine came up with a way to help autistic children to identify facial expressions by pairing an app on smartphones with Google Glass. Google Glass is a set of special glasses the children wear that is linked with a smartphone through a local wireless network. It consists of a glasses-like frame equipped with a camera to record what the wearer is seeing, and a small screen and a speaker to give the wearer visual and audio information. As the child interacts with others, the app identifies and names their emotions through the Google Glass speaker or screen. After 1 – 3 months of regular use, parents reported that children with autism made more eye contact and related better to others.
This technology is still new, so children today, diagnosed with autism, generally have to wait around 18 months to receive treatment. Stanford says the treatment could help fill a major gap in autism care, but right now, there is a shortage of trained therapists. Early autism therapy has been shown to be particularly effective, but many children aren’t treated quickly enough to get the maximum benefit. The best way to solve that problem is to create reliable, home-based treatment systems. Stanford believes they have come up with that way by using their app with Google Glass.
The researchers named the new therapy “Superpower Glass” to help make it appealing to children. The therapy is based on applied behavior analysis, which helps autistic children by using flash cards, but it must be handled on a one-on-one basis by trained therapists, and flash cards can’t always capture the full range of human emotion. Autistic children have struggled sometimes to transfer what they learn to their daily lives.
To help with that, Stanford built a smartphone app that uses machine learning to recognize eight core facial expressions: happiness, sadness, anger, disgust, surprise, fear, neutral and contempt. The app was trained with hundreds of thousands of photos of faces showing the eight expressions, and also had a mechanism to allow people involved in the study to calibrate it to their own ‘neutral’ faces if necessary.
In Stanford’s study, the researchers used 14 families with autistic children to test the Superpower Glass setup at home for around 10 weeks. The families used the therapy for at least three 20-minute sessions per week. Before and after the study, the parents completed questionnaires to provide detailed information about their child’s social skills. They also gave interviews about how the program worked for their families.
Stanford designed three ways to use the program. In ‘free play, children wear Google Glass while interacting or playing with their families. The software provides the child with a visual or auditory cue each time it recognizes an emotion on the face of someone the child sees. Then there are the two game modes. In ‘guess my emotion,’ a parent acts out a facial expression corresponding to one of the eight core emotions, and the child tries to identify it. The game also helps families and researchers track the children’s improvement at identifying emotions. In ‘capture the smile,’ children give another person clues about the emotion they want to elicit until the person acts it out. This helps the researchers gauge the children’s understanding of the different emotions. The families have reported great success with this technology.
Stanford is now working on a larger, randomized trial of the therapy. They also plan to test the therapy on children who have just been diagnosed with autism and are on a waiting list for treatment. They have also filed a patent application for the technology. So. . . looks like things are looking up now for the little ones.