In 1995 French form magazine editor Jean-Dominique Bauby suffered a seizure while driving a car which left him with a state known as locked-in syndrome a neurological disease in which the resigned is fully paralyzed and can only move muscles that control the eyes.
Bauby who had signed a book contract shortly precedently his chance wrote the biographical ’The Diving Bell and the Butterfly’ using a imperative method in which his address therapist recited the alphabet and he would wink when she said the correct epistle. They wrote the 130-page book one wink at a time.
Technology has come a long way since Baubys chance. Many personals with serious motor impairments caused by locked-in syndrome cerebral palsy amyotrophic indirect sclerosis or other states can adjoin using computer interfaces where they select epistles or words in an onscreen grid by activating a one switch frequently by urgent a button releasing a puff of air or winking.
But these row-column scanning methods are very stiff and correspondent to the technique used by Baubys address therapist they highlight each discretion one at a time making them frustratingly slow for some users. And they are not suitable for tasks where discretions cant be arranged in a grid like drawing browsing the web or gaming.
A more pliant method being educeed by investigationers at MIT places personal choice indicators next to each discretion on a computer screen. The indicators can be placed anywhere — next to anything someone might click with a mouse — so a user does not need to cycle through a grid of choices to make choices. The method named Nomon incorporates probabilistic reasoning to acquire how users make choices and then harmonizes the interface to better their despatch and exactness.
Participants in a user study were able to type faster using Nomon than with a row-column scanning method. The users also accomplished better on a picture choice task demonstrating how Nomon could be used for more than typing.
’It is so cool and exciting to be able to educe software that has the practicable to veritably help nation. Being able to find those signals and turn them into communication as we are used to it is a veritably interesting problem’ says senior creator Tamara Broderick an companion professor in the MIT Department of Electrical Engineering and Computer Science (EECS) and a limb of the Laboratory for Information and Decision Systems and the Institute for Data Systems and Society.
Joining Broderick on the paper are lead creator Nicholas Bonaker an EECS graduate student; Emli-Mari Nel head of alteration and machine acquireing at Averly and a visiting lecturer at the University of Witwatersrand in South Africa; and Keith Vertanen an companion professor at Michigan Tech. The investigation is being presented at the ACM Conference on Human Factors in Computing Systems.
On the clock
In the Nomon interface a pliant analog clock is placed next to see discretion the user can select. (A gnomon is the part of a sundial that casts a umbration.) The user looks at one discretion and then clicks their switch when that clocks hand passes a red ’noon’ line. After each click the method changes the phases of the clocks to separate the most likely next targets. The user clicks frequently until their target is selected.
When used as a keyboard Nomons machine-acquireing algorithms try to conjecture the next word based on antecedent words and each new epistle as the user makes choices.
Broderick educeed a simplified rendering of Nomon separate years ago but determined to revisit it to make the method easier for motor-impaired personals to use. She enlisted the help of then-undergraduate Bonaker to redesign the interface.
They leading consulted nonprofit organizations that work with motor-impaired personals as well as a motor-impaired switch user to gather feedback on the Nomon design.
Then they designed a user study that would better portray the abilities of motor-impaired personals. They wanted to make sure to thoroughly vet the method precedently using much of the precious time of motor-impaired users so they leading tested on non-switch users Broderick explains.
Switching up the switch
To gather more portrayative data Bonaker devised a webcam-based switch that was harder to use than simply clicking a key. The non-switch users had to lean their bodies to one side of the screen and then back to the other side to register a click.
’And they have to do this at precisely the right time so it veritably slows them down. We did some experimental studies which showed that they were much closer to the response times of motor-impaired personals’ Broderick says.
They ran a 10-session user study with 13 non-switch participants and one one-switch user with an advanced form of spinal strong dystrophy. In the leading nine sessions participants used Nomon and a row-column scanning interface for 20 minutes each to accomplish text entrance and in the 10th session they used the two methods for a picture choice task.
Non-switch users typed 15 percent faster using Nomon while the motor-impaired user typed even faster than the non-switch users. When typing unfamiliar words the users were 20 percent faster overall and made half as many faults. In their terminal session they were able to complete the picture choice task 36 percent faster using Nomon.
’Nomon is much more forgiving than row-column scanning. With row-column scanning even if you are just slightly off now youve chosen B instead of A and thats an fault’ Broderick says.
Adapting to loud clicks
With its probabilistic reasoning Nomon incorporates seething it knows almost where a user is likely to click to make the process faster easier and less fault-prone. For entreaty if the user selects ’Q’ Nomon will make it as easy as practicable for the user to select ’U’ next.
Nomon also acquires how a user clicks. So if the user always clicks a pliant behind the clocks hand strikes noon the method adapts to that in real time. It also adapts to noisiness. If a users click is frequently off the mark the method requires extra clicks to fix exactness.
This probabilistic reasoning makes Nomon strong but also requires a higher click-load than row-column scanning methods. Clicking multiple times can be a trying task for seriously motor-impaired users.
Broderick hopes to lessen the click-load by incorporating gaze tracking into Nomon which would give the method more strong information almost what a user might select next based on which part of the screen they are looking at. The investigationers also want to find a better way to automatically harmonize the clock despatchs to help users be more careful and efficient.
They are working on a new series of studies in which they plan to associate with more motor-impaired users.
’So far the feedback from motor-impaired users has been inprecious to us; were very pleasant to the motor-impaired user who commented on our initial interface and the separate motor-impaired user who participated in our study. Were currently extending our study to work with a bigger and more diverse cluster of our target population. With their help were already making further betterments to our interface and working to better apprehend the accomplishance of Nomon’ she says.
’Nonspeaking personals with motor disabilities are currently not granted with efficient communication solutions for interacting with whichever speaking associates or computer methods. This communication gap is a known unresolved problem in human-computer interaction and so far there are no good solutions. This paper demonstrates that a greatly creative access underpinned by a statistical standard can prepare palpable accomplishance gains to the users who need it the most: nonspeaking personals reliant on a one switch to adjoin’ says Per Ola Kristensson professor of interactive methods engineering at Cambridge University who was not implicated with this investigation. ’The paper also demonstrates the value of complementing insights from computational experiments with the involvement of end-users and other stakeholders in the design process. I find this a greatly creative and expressive paper in an area where it is notoriously hard to make expressive progress.’
This investigation was supported in part by the Seth Teller Memorial Fund to Advanced Technology for People with Disabilities a Peter J. Eloranta Summer Undergraduate Research Fellowship the MIT Quest for Intelligence and the National Science Foundation.