|Title:||Non-intrusive multimodal attention detection|
Hong Kong Polytechnic University -- Dissertations
|Department:||Department of Computing|
|Pages:||iii, 47 leaves : illustrations (some color) ; 30 cm|
|Abstract:||With the increasing deployment of computes in a wide variety of applications, the ability to detect the user's attention, or engagement, as a key piece of contextual information is becoming more important in building effective interactive systems. The idea is that a system being aware of whether the user is attending to it would be able to adapt itself better to the user activities to enhance productivity. Much previous work in attention detection are either obtrusive or impose demanding constraints on the context and the participants. In addition, most approaches rely on uni-modal signals, often with limited availability and stability. This research attempts to address these two major limitations through a non-intrusive multimodal solution that allows participants to work naturally and without interference. The solution makes use of common off-the-shelf items that could reasonably be expected of any computing environment and does not rely on expensive and tailor-made equipment. With a three-class attention state setting, it achieves average accuracy rates of 59.63% to 77.81%; the best result being 77.81% for a searching task, which shows 11.9% improvement over the baseline. Analysis and discussion on contribution by individual feature to different models are presented in this dissertation.|
|Rights:||All rights reserved|
Files in This Item:
|b27576723.pdf||For All Users (off-campus access for PolyU Staff & Students only)||1.12 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: