Thesis Topic Details

Topic ID:
2936
Title:
Intelligent Desktop using Bayesian Filtering
Supervisor:
Maurice Pagnucco
Research Area:
Artificial Intelligence
Associated Staff
Assessor:
Alan Blair
Topic Details
Status:
Active
Type:
R & D
Programs:
CS CE BIOM BINF SE
Group Suitable:
No
Industrial:
No
Pre-requisites:
COMP3411
Description:
As computers become more common in our daily lives there is a need to perform computing tasks more quickly and effectively. In this project we aim to investigate the development of an intelligent desktop user interface that anticipates user needs. This is achieved using a Bayesian filtering technique. The use of this technique has been successfully applied in other products. For example, in MS Windows, the help feature uses Bayesian filtering to determine the best response to provide for a user's help query. We adapt this technique in this project to the user's desktop in order to build a software tool that attempts to anticipates user needs and respond to them quickly and effectively.


References:

* D Heckerman, D Chickering, C Meek, R Rounthwaite, Dependency networks for collaborative filtering and data visualization , in Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, 2000.

* E Horvitz, M Shwe, In Pursuit of Effective Handsfree Decision Support: Coupling Bayesian Inference, Speech Understanding , in Proceeedings of the 19th Annual Symposium of Computer Applications, 1995.
Comments:
--
Past Student Reports
 
No Reports Available. Contact the supervisor for more information.

Check out all available reports in the CSE Thesis Report Library.

NOTE: only current CSE students can login to view and select reports to download.