Artificial Intelligence has transformed the world of assistive technology and inclusive environments.
This list of articles was originally created as a self-guided pathway within Intuit’s Accessibility documentation. It provides an insight into inclusive research with Machine Learning and Artificial Intelligence. Research like this is continually evolving and the articles below may already be out of date. But they’ll lead you to information you may not have known.
Artificial Intelligence Enhances Accessibility for People with Disabilities (Inclusive City Maker)
Through examples of artificial intelligence technology solutions, discover how accessibility for people with disabilities can be enhanced!
Glenda Watson Hyatt discusses her experiences in a pilot study for neuroplasticity and rehabilitation.
Results from the clinical trial with subjects with mild to moderate TBIs will be known in three months. Two other conditions – and very possible a third in a year – are slated for clinical trials using the PoNS. I am hesitant to name the three conditions at this point because I don’t know if it is public knowledge, yet. (Everything else shared here is available online.) It is suffice to say that I am extremely excited, both for myself and many of my friends and colleagues.
As I mentioned in an email to Lynda, I am not looking for a miraculous cure, to be walking straight and talking clearly. But, what if some improved functioning is possible? What if more controlled movement is possible? What if I could deliver a speech, using my iPad, without being so tense and jerky on stage? What if I could get through an average day without being totally exhausted?
Today’s mobility solutions use micro sensors and neural networks to change the way we move through our worlds.
ReWalk is a wearable robotic exoskeleton that provides powered hip and knee motion to enable individuals with spinal cord injury (SCI) to stand upright, walk, turn, and climb and descend stairs*. ReWalk is the first exoskeleton to receive FDA clearance for personal and rehabilitation use in the United States.
The latest features in Microsoft’s Seeing AI app enable the app to recognize things in the world and place them in 3D space. Items are literally announced from their position in the room; in other words, the word “chair” seems to emanate from the chair itself. Users can place virtual audio beacons on objects to track the location of the door, for example, and use the haptic proximity sensor to feel the outline of the room.
Getting around: Autonomous Vehicles, Ride-Sharing and Those Last Few Feet
Summoning a ride from a smart phone is a dream come true for many, but when you have difficulty finding that ride, even when it’s a few feet away, the experience can be a nightmare, not to mention dangerous. How are ride-share and autonomous taxi companies working to make those last few feet from rider-to-car safer and better for blind and low vision riders?
Sunu Band – Sonar powered wearable for navigation
The Sunu Band is a smart band that protects your head and upper body by warning you through vibrations when an object or person is too close. You wear it like a watch and it will feel like walking with an invisible sighted guide, helping you get anywhere you want to go and keeping you safe at all times.
Communication and Learning
Learn how AI is being used to diagnose dyslexia, increase readability and education, and hearing comprehension.
DysWebxia – AI powered reading for people with Dyslexia
DysWebxia is a model that integrates the findings from the PhD thesis of Luz Rello (June 2014) that includes studies with more than 150 people with dyslexia using eye tracking to make the texts more readable by modifying the content and presentation of the text. This research was conducted with funding from Generalitat de Calaluyna (FI doctoral fellowship) at Web Research Group & Natural Language Processing Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra.
The aim of our web-game called MusVis (see Video) is to measure the reaction of children with and without dyslexia while playing, in order to find differences on their behavior. Dyslexia is a specific learning disorder that affects from 5% to 15% of the world population. To the best of our knowledge, this is the first time that risk of dyslexia is screened using a language-independent content web-based game and machine-learning.
Authors: Maria Rauschenberger Ricardo Baeza-Yates Luz Rello
Children with dyslexia are often diagnosed after they fail school even if dyslexia is not related to general intelligence. In this work, we present an approach for universal screening of dyslexia using machine learning models with data gathered from a web-based language-independent game. We designed the game content taking into consideration the analysis of mistakes of people with dyslexia in different languages and other parameters related to dyslexia like auditory perception as well as visual perception. We did a user study with 313 children (116 with dyslexia) and train predictive machine learning models with the collected data. Our method yields an accuracy of 0.74 for German and 0.69 for Spanish as well as a F1-score of 0.75 for German and 0.75 for Spanish, using Random Forests and Extra Trees, respectively. To the best of our knowledge this is the first time that risk of dyslexia is screened using a language-independent content web-based game and machine-learning. Universal screening with language-independent content can be used for the screening of pre-readers who do not have any language skills, facilitating a potential early intervention.
Progressive Accessibility Solutions – AI powered inclusive education for math and science
Create STEM material that give your students a fully accessible interactive learning experience. Ensure that all your institution’s online teaching and examination is accessible and inclusive for everyone. Train your teachers, faculty and staff on how to plan and prepare fully accessible STEM courses.
Imagine wanting to express yourself but bottling it all up because you cant. Life is so challenging for people who cannot find the medium to say what they have to. People with paralysis, dysfunctional upper limbs, or ALS(amyotrophic lateral sclerosis) use facial movements and gestures to talk. However, researchers have shared a glimpse of the future where an experiment successfully showed computers turning signals to digital text.
Harnessing the power of artificial intelligence to transform hearing healthcare and research (Nature Machine Intelligence)
The advances in artificial intelligence that are transforming many fields have yet to make an impact in hearing. Hearing healthcare continues to rely on a labour-intensive service model that fails to provide access to the majority of those in need, while hearing research suffers from a lack of computational tools with the capacity to match the complexities of auditory processing. This Perspective is a call for the artificial intelligence and hearing communities to come together to bring about a technological revolution in hearing. We describe opportunities for rapid clinical impact through the application of existing technologies and propose directions for the development of new technologies to create true artificial auditory systems. There is an urgent need to push hearing towards a future in which artificial intelligence provides critical support for the testing of hypotheses, the development of therapies and the effective delivery of care worldwide. AI has impacted many fields, but hearing has lagged behind. This Perspective calls for a collaboration between the AI and hearing communities, with the goal of transforming hearing healthcare and research.
GPS makes it easy to get from point A to point B. But it leaves a gap for the last 20 feet and when you walk indoors. These projects are solving these issues.
Personal Dead Reckoning for GPS denied environments – Johann Borenstein The University of Michigan
Personal Dead-reckoning System for GPS-denied Environments Lauro Ojeda. This paper introduces a positioning system for walking persons, called “Personal Dead-reckoning” (PDR) system. The PDR system does not require GPS, beacons, or landmarks. The system is therefore useful in GPS-denied environments, such as inside build- ings, tunnels, or dense forests.
Clew is a path retracing app designed for blind and visually impaired users to help them independently return to any desired locations. Using Apple’s new ARKit built for iOS 11 devices, Clew records a path and guides the user back to their starting location with a choice of voice directions, sound effects, and haptic feedback.
Indoor Navigation: Can Inertial Navigation, Computer Vision and other new technologies Work Where GPS Can’t?
Thanks to mobile phones, GPS, and navigation apps, people who are blind or visually impaired can get around outdoors independently. Navigating indoors is another matter. For starters, GPS is often not available indoors. Then there are the challenges of knowing where the door is, finding the stairs, or avoiding the couch someone moved.
Engineer Brandon Biggs at Smith-Kettlewell Eye Research Institute demonstrates our indoor wayfinding app in development.
Life can be enhanced in many ways with Artificial Intelligence. Here are several examples.
The best enhanced vision device is ready for life on the go. eSight is used daily by thousands of people with over 20 different serious eye conditions causing visual acuity from 20/60 to 20/800, and in some cases up to 20/1400. Built upon its clinically-validated technology, eSight 4 takes sight enhancement to a new level.
Designing for Everyone: Accessibility and Machine Learning at Apple
Apple’s iPhone and VoiceOver are among the greatest breakthroughs ever for accessibility but Apple never rests on its laurels. The next wave of innovation will involve what’s known as “machine learning” (a subset of artificial intelligence), which uses data from sensors on the phone and elsewhere to help make sense of the world around us.
Today we announced a significant reduction in our use of facial recognition technology, including the deletion of face recognition templates that we previously used to identify faces in photos. This means automatic alt text will still be able to recognize when a person is in a photo, but it will no longer include names of people.
The gene editor CRISPR excels at fixing disease mutations in lab-grown cells. But using CRISPR to treat most people with genetic disorders requires clearing an enormous hurdle: getting the molecular scissors into the body and having it slice DNA in the tissues where it’s needed. Now, in a medical first, researchers have injected a CRISPR drug into the blood of people born with a disease that causes fatal nerve and heart disease and shown that in three of them it nearly shut off production of toxic protein by their livers.
Lookout uses computer vision to assist people with low vision or blindness get things done faster and more easily. Using your phone’s camera, Lookout makes it easier to get more information about the world around you and do daily tasks more efficiently like sorting mail, putting away groceries, and more.
AI and depression are not the words you’d combine into one sentence five years ago. Today, however, intelligent depression is making headway. AI depression apps and AI treatment are stepping in to replace imprecise dated methods to diagnose mental illnesses. And we couldn’t have chosen a better timing.