Abstract
Eye-tracking technology is advancing rapidly, becoming cheaper and easier to use and more robust. This has fueled an increase in its implementation for Augmentative and Alternative Communication (AAC). Nowadays, Eye-Tracking Communication Devices (ETCDs) can be an effective aid for people with disabilities and communication problems. However, it is not clear what level of performance is attainable with these devices or how to optimize them for AAC use. The objective of this observational study was to provide data on non-disabled adults' performance with ETCD regarding (a) range of eye-typing ability in terms of speed and errors for different age groups and (b) relationship between ETCD performance and bimanual writing with a conventional PC keyboard and (c) to suggest a method for a correct implementation of ETCD for AAC. Sixty-seven healthy adult volunteers (aged 20–79 years) were asked to type a sample sentence using, first, a commercial ETCD and then a standard PC keyboard; we recorded the typing speed and error rate. We repeated the test 11 times in order to assess performance changes due to learning. Performances differed between young (20–39 years), middle-aged (40–59 years), and elderly (60–79 years) participants. Age had a negative impact on performance: as age increased, typing speed decreased and the error rate increased. There was a clear learning effect, i.e., repetition of the exercise produced an improvement of performance in all subjects. Bimanual and ETCD typing speed showed a linear relationship, with a Pearson's correlation coefficient of 0.73. The assessment of the effect of age on eye-typing performance can be useful to evaluate the effectiveness of man-machine interaction for use of ETCDs for AAC. Based on our findings, we outline a potential method (obviously requiring further verification) for the setup and tuning of ETCDs for AAC in people with disabilities and communication problems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Similar Papers
More From: Computational Intelligence and Neuroscience
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.