Interaction with the surrounding environment is an essential element of ever day life. For individuals with severe motor and communicative disabilities, single switch scanning is used as method to control their environment and communicate. Despite being very slow, it is often the only option for individuals who cannot use other interfaces. The alteration of timing parameters and scanning system configurations impacts the communication rate of those using single switch scanning. The ability to select and recommend an efficient configuration for an individual with a disability is essential.
Predictive models could assist in the goal of achieving the best possible match between user and assistive technology device, but consideration of an individuals single switch scanning tendencies has not been included in communication rate prediction models. Modeling software developed as part of this research study utilizes scan settings, switch settings, error tendencies, error correction strategies, and the matrix configuration to calculate and predict a communication rate.
Five participants with disabilities who use single switch scanning were recruited for this study. Participants were asked to transcribe sentences using an on-screen keyboard configured with settings used on their own communication devices. The participants error types, frequencies, and correction methods were acquired as well as their text entry rate (TER) during sentence transcription. These individual tendencies and system configuration were used as baseline input parameters to a scanning model application that calculated a TER based upon those parameters. The scanning model was used with the participants tendencies and at least three varied system configurations. Participants were asked to transcribe sentences with these three configurations The predicted TERs of the model were compared to the actual TERs observed during sentence transcription for accuracy. Results showed that prediction were 90% accurate on average. Model TER predictions were less than one character per minute different from observed baseline TER for each participant. Average model predictions for configuration scenarios were less than one character per minute different from observed configuration TER.
| Identifer | oai:union.ndltd.org:PITT/oai:PITTETD:etd-07262009-195906 |
| Date | 10 September 2009 |
| Creators | Mankowski, Robert E. |
| Contributors | Dr. Edmund LoPresti, Dr. Richard C. Simpson, John Coltellaro |
| Publisher | University of Pittsburgh |
| Source Sets | University of Pittsburgh |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.library.pitt.edu/ETD/available/etd-07262009-195906/ |
| Rights | unrestricted, I hereby certify that, if appropriate, I have obtained and attached hereto a written permission statement from the owner(s) of each third party copyrighted matter to be included in my thesis, dissertation, or project report, allowing distribution as specified below. I certify that the version I submitted is the same as that approved by my advisory committee. I hereby grant to University of Pittsburgh or its agents the non-exclusive license to archive and make accessible, under the conditions specified below, my thesis, dissertation, or project report in whole or in part in all forms of media, now or hereafter known. I retain all other ownership rights to the copyright of the thesis, dissertation or project report. I also retain the right to use in future works (such as articles or books) all or part of this thesis, dissertation, or project report. |
Page generated in 0.0123 seconds