1 / 29

URICA: Usage-awaRe Interactive Content Adaptation for Mobile Devices

URICA is a system that allows users to interactively refine the adaptation decisions made by the system for mobile devices, improving content customization based on user preferences and usage patterns.

skessler
Download Presentation

URICA: Usage-awaRe Interactive Content Adaptation for Mobile Devices

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. URICA: Usage-awaRe Interactive Content Adaptationfor Mobile Devices Iqbal Mohomed, Jim Chengming Cai and Eyal de Lara Department of Computer Science University of Toronto EuroSys2006: Session 10 – User Studies

  2. Heterogeneity in Mobile Devices • Significant Resource Variability among Mobile Devices • Screen real-estate • Networking • Battery Life • User Interface • Memory • Processing Capability

  3. Need for Adaptation Downloaded Data  600KB Content must be customized!

  4. Manual Adaptation • Publishers make available content for several classes of devices • e.g., HTML and WAP versions of Web page • Disadvantages: High human cost • Done for every device (multiple versions) • Maintaining consistency and coherence • You can never cover all possible versions! • Continuous effort to support new types of devices • In practice: • Only done for few high-traffic sites • Limited number of devices • Slow update propagation • Not Scalable

  5. Automatic Adaptation Mobile Device Adaptation Proxy Unmodified Content Server We Have The Mechanism But … The Hard Problem is Policies!

  6. Achieving Fine Grain Adaptation • Usage affects the customization that is needed • Machines have a hard time distinguishing between good and bad adaptations • People are better

  7. Achieving Fine Grain Adaptation • Usage affects the customization that is needed • Machines have a hard time distinguishing between good and bad adaptations • People are better • Users performing same task on content have similar adaptation requirements • Rely on a few users to adapt content for everyone

  8. Usage-awaRe Interactive Content Adaptation (URICA) • Allow users to interactively refine system’s adaptation decision • System learns from user modifications • Uses history for future adaptation predictions • Applicable to a wide range of adaptation types, such as image fidelity and page layout

  9. 40KB Server 1 Improve Fidelity Server 2 Mobile 2 Application 10KB 20KB Prediction How it Works Mobile 1 Application Adaptation Proxy

  10. Chameleon – a URICA prototype • Reduces bandwidth consumption and download latencies • Image Fidelity Adaptation System • Transcodes JPEG images on-the-fly to reduce file size • Uses history for prediction • Pocket Internet Explorer for PocketPC PDAs • Users can tap on images to improve fidelity

  11. Adaptation Requirements Locality in user preferences Variation due to task and user preferences

  12. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency

  13. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Start 2 3 4 5 Bandwidth Optimal

  14. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  15. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  16. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  17. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  18. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  19. Chameleon Prediction Policies • Minimizing bandwidth consumption or the number of user interactions required is trivial! • However, may not result in optimal latency Download Time per Slice: 3 seconds User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Start 2 3 4 5

  20. Personalized Adaptation Schedule • Optimizes expected fulfillment time • Time to reach fidelity level that satisfies user • Includes download and interaction time • Determines optimal personalized adaptation schedule • List of predictions • Schedule based on • Object adaptation history • Immediate bandwidth • User interaction time

  21. PAS In Operation User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Download Time per Slice: 3 seconds BW Optimal Start 2 3 4 5

  22. PAS In Operation User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Download Time per Slice: 3 seconds BW Optimal Start 2 3 4 5 Start 3 4 5 PAS

  23. PAS In Operation User’s Average Interaction Time: 2 seconds User’s Desired Fidelity: 4 Download Time per Slice: 3 seconds BW Optimal Start 2 3 4 5 Start 3 4 5 PAS Download Time per Slice: 1 second Start 5 PAS

  24. User Study • 30 Participants • 3 Web sites • Word Recognition and Photo Album web site – all users doing the same task • Poster Ads web site – 3 groups, each with distinct task • PDA with CDMA 1X Network Connectivity (66-100Kbps) • Prediction Mechanism was disabled • Chameleon initially served images at fidelity 1 • Users tapped on images to get next fidelity • Experiments performed on collected traces

  25. Fulfillment Time Optimization – Single Task Adaptation can improve fulfillment time PAS has near-optimal performance

  26. Fulfillment Time Optimization – Multiple Tasks Optimal behavior requires taking into account bandwidth and interaction time along with history

  27. Fulfillment Time As Bandwidth Changes PAS is flexible Mean’s problems exacerbate

  28. Additional Results in Paper • PAS can be used to achieve a desired tradeoff between bandwidth consumption and the number of required interactions • Users can specify a cost for having to interact with the system to correct the adaptation • Effect of User Interface on Adaptive Behavior of Users

  29. http://adaptive.cs.toronto.edu/ Summary Questions? • URICA is a general-purpose automatic content adaptation technique • Learns from user corrections to adaptation decisions • Chameleon is an image fidelity adaptation system that can be used to: • optimize fulfillment time • reduce bandwidth consumption • achieve user’s desired tradeoff between bandwidth consumption and the need to provide interactions

More Related