The University of Miami recently posted about their “Behavioral Imaging of Autism” study at the Center for Autism and Related Disabilities (CARD). The study utilizes digitally collected data to diagnose patients. In the above photo Amy Ahn works with a toddler while wearing glasses that record facial expressions and gestures. This data will be used to develop technologies that will assist clinicians in diagnosing Autism Spectrum Disorder (ASD). A main goal of the study is to identify technologies that can improve access to diagnoses as well as diagnose patients earlier leading to earlier interventions.
…the earlier children are diagnosed, the quicker they can take advantage of interventions that can improve their lives dramatically.
This study includes a collaboration with Mei-Ling Shyu’s lab in the Department of Engineering at the University of Miami. They recently submitted an abstract to be presented at the 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). The abstract describes the ‘SP-ASDNet’ model, this classifier utilizes long short-term memory networks and convolution neural networks. Using visual data of a participant’s scanpath (when looking at an image) it is able to classify patient’s with ASD. Currently the SP-ASDNet was able to achieve 74.22% accuracy which is close to psychologists diagnosis rate of 70%.
There are a number of groups working towards machine learning assisted diagnosis of ASD. If you would like to learn more about CARD at the University of Miami checkout their website. If you’d like to learn more about machine learning approaches to diagnose ASD here is a helpful review.
We are angry, frustrated, and in pain because of the violence and murder of Black people by the police because of racism. We are in the fight AGAINST RACISM. George Floyd was murdered, his life stolen. The Adafruit teams have specific actions we’ve done, are doing, and will do together as a company and culture. We are asking the Adafruit community to get involved and share what you are doing. The Adafruit teams will not settle for a hash tag, a Tweet, or an icon change. We will work on real change, and that requires real action and real work together. That is what we will do each day, each month, each year – we will hold ourselves accountable and publish our collective efforts, partnerships, activism, donations, openly and publicly. Our blog and social media platforms will be utilized in actionable ways. Join us and the anti-racist efforts working to end police brutality, reform the criminal justice system, and dismantle the many other forms of systemic racism at work in this country, read more @ adafruit.com/blacklivesmatter
Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.