On power-law relationships of the Internet topology
Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Computer
Using GPS to learn significant locations and predict movement across multiple users
Personal and Ubiquitous Computing
Extracting places from traces of locations
ACM SIGMOBILE Mobile Computing and Communications Review
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
International Journal of Robotics Research
Active GSM cell-id tracking: "Where Did You Disappear?"
Proceedings of the first ACM international workshop on Mobile entity localization and tracking in GPS-less environments
Proximity classification for mobile devices using wi-fi environment similarity
Proceedings of the first ACM international workshop on Mobile entity localization and tracking in GPS-less environments
Place lab: device positioning using radio beacons in the wild
PERVASIVE'05 Proceedings of the Third international conference on Pervasive Computing
Learning and recognizing the places we go
UbiComp'05 Proceedings of the 7th international conference on Ubiquitous Computing
SensLoc: sensing everyday places and paths using less energy
Proceedings of the 8th ACM Conference on Embedded Networked Sensor Systems
Designing for context-aware health self-monitoring, feedback, and engagement
Proceedings of the ACM 2011 conference on Computer supported cooperative work
Deliberation for intuition: a framework for energy-efficient trip detection on cellular phones
Proceedings of the 13th international conference on Ubiquitous computing
A habit mining approach for discovering similar mobile users
Proceedings of the 21st international conference on World Wide Web
Can crowdsensing beat dynamic cell-ID?
Proceedings of the Third International Workshop on Sensing Applications on Mobile Phones
| Hi-index | 0.00 |
In this paper we propose a mass market solution on mobile phones to discover a user's significant places solely from observed cell IDs. It does not require either cell-ID-to-physical-location mapping or the capability of obtaining multiple cell IDs on the phone simultaneously, and is able to run on virtually any mobile phone today. Our solution is centered around a cell ID clustering algorithm based on temporal correlations. It is able to prevent over-clustering and handles missing data well. We evaluate the solution with real-life data that the author has collected over a period of eight weeks. Results show that we are able to discover not only places of utter importance, but also certain less frequently recurring places and one-time travel destinations that bear significance in one's life.