Wherehoo and Periscope: a time & place server and tangible browser for the real world
CHI '01 Extended Abstracts on Human Factors in Computing Systems
Using Low-Cost Sensing to Support Nutritional Awareness
UbiComp '02 Proceedings of the 4th international conference on Ubiquitous Computing
Video shot segmentation using singular value decomposition
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1
Place-Its: a study of location-based reminders on mobile phones
UbiComp'05 Proceedings of the 7th international conference on Ubiquitous Computing
Opportunities exist: continuous discovery of places to perform activities
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Myngle: unifying and filtering web content for unplanned access between multiple personal devices
Proceedings of the 13th international conference on Ubiquitous computing
Hi-index | 0.00 |
People rapidly learn the capabilities of a new location, without observing every service and product. Instead they map a few observations to familiar clusters of capabilities. This paper proposes a similar approach to computer discovery of routine location capabilities, applying machine learning to predict unobserved capabilities based on a combination of a small body of local observations and a larger body of data that is not specific to the location. We propose using the time and place of deleting items from a to-do list application to provide the local data. For reminder purposes, an area within easy walking distance is a single location, but may contain many different shops and services, collectively offering its own combination of capabilities. Truncated singular value decomposition maps the observations to combinations of features, rather than to a single cluster. Simulations, using distributions derived from real world data, demonstrate the feasibility of this approach.