Click here to skip to this page's main content.

New to the Open Library? — Learn how it works
Want to support Open Library? Until April 30, we'll double your donation! Help us build the great digital library.
Last edited by WorkBot
January 24, 2010 | History

Message prediction for an icon-based pediatric communication aid 1 edition

Message prediction for an icon-based pediatric communication aid
Daniel Cossever

No ebook available.


Prefer the physical book? Check nearby libraries powered by WorldCat


¬°Ay, caramba! There's no description for this book yet. Can you help?
There is only 1 edition record, so we'll show it here...  •  Add edition?

Message prediction for an icon-based pediatric communication aid.

Published 2005 .
Written in English.

About the Book

Various methods for predicting outputs in an icon-based pediatric communication aid are explored. These include a time-based frequency counter, statistical analysis based on previous selections, and feed-forward neural networks. In order to properly train the prediction mechanisms, a large amount of data are required. This thesis develops and evaluates two methods for data generation when little or no labeled communication data is available. The first method is to use a family member's knowledge of the communication patterns of the patient, and the second is to use the dependencies found during the patient's initial device usage to generate additional sequences. With a single subject in critical care, it was found that a neural network predictor based on a backpropagation algorithm achieved the highest prediction rate. The minimum amount of empirically collected data required to generate useful training sequences, and the minimum length of generated sequences to adequately train the predictors are also investigated.

Edition Notes

Source: Masters Abstracts International, Volume: 44-02, page: 0956.

Thesis (M.Sc.)--University of Toronto, 2005.

Electronic version licensed for access by U. of T. users.

GERSTEIN MICROTEXT copy on microfiche (2 microfiches).

The Physical Object

Pagination
129 leaves.
Number of pages
129

ID Numbers

Open Library
OL19216138M
ISBN 10
0494070994

History Created December 11, 2009 · 2 revisions Download catalog record: RDF / JSON

January 24, 2010 Edited by WorkBot add more information to works
December 11, 2009 Created by WorkBot add works page