Bradley Wachter, a senior undergraduate in the Ability & Innovation Lab, is featured in the Mechanical Engineering student research spotlight for his work designing and building orthoses. Great job, Bradley!
To read more, click here.
Bradley Wachter, a senior undergraduate in the Ability & Innovation Lab, is featured in the Mechanical Engineering student research spotlight for his work designing and building orthoses. Great job, Bradley!
To read more, click here.
The University of Washington’s new program Husky ADAPT was featured on King 5 news during a toy adaptation workshop.
We adapted toys to allow for a variation of accessible switches to be used by children with diverse abilities. This way, instead of having to use a large degree of force to activate a typical hard to reach ON/OFF switch, children and adults alike can use a switch that works best for them to interact, learn, and most importantly play. This workshop also served to educate engineers about universal design.
What if we didn’t have to adapt toys? What if more toys were accessible off-the-shelf to individuals with diverse abilities? Hopefully all the students will remember these small lessons as they design products and environments in the future.” -Kat Steele
To read about the toy adaptation as posted on the ME Departmental website, follow this LINK or CLICK HERE if on campus.
http://www.king5.com/news/local/seattle/toy-hackers-help-kids-with-disabilities/367898045
Peer-reviewed paper at European Conference on Computer Vision:
30-second videos from a depth camera can be used in the evaluation of infants with spinal muscular atrophy.
Abstract: Spinal Muscular Atrophy is the most common genetic cause of infant death. Due to its severity, there is a need for methods for automated estimation of disease progression. In this paper we propose a Convolutional-Neural-Network (CNN) model to estimate disease progression during infants’ natural behavior. With the proposed methodology, we were able to predict each child’s score on current behavior-based clinical exams with an average per-subject error of 6.96 out of 72 points (<10 % difference), using 30-second videos in leave-one-subject-out-cross-validation setting. When simple statistics were used over 30-second video-segments to estimate a score for longer videos, we obtained an average error of 5.95 (∼8 % error rate). By showing promising results on a small dataset (N = 70, 2-minute samples, which were handled as 1487, 30-second video segments), our methodology demonstrates that it is possible to benefit from CNNs on small datasets by proper design and data handling choices.
Congratulations to Jessica for being acknowledged by the Department of Mechanical Engineering for her academic achievements and potential for success within her masters studies.
Jessica is dedicated to creating a pediatric exoskeleton which promotes improved walking patterns during daily life, outside of therapy sessions. This fellowship will allow Jessica to devote more time towards her research and studies. Congrats!
Here at the Ability & Innovation Lab we are fortunate to partner with amazing families and people who are our user experts for feedback and ideas when creating new devices and designs. Jayna and her family are fantastic partners in the design project for Jayna, alongside our undergraduate students. The second prototype is now underway to improve the comfort, donning and doffing, and applicability of Jayna’s elbow-driven device to enable the use of her left arm during two handed tasks.
UW Together presents Jayna’s story HERE.