Large-Scale Human Context Discovery from Mobile Phones
LS-CONTEXT (Large-Scale Human Context Discovery from Mobile Phones) will investigate probabilistic methods to discover personal and social behavioral patterns from cell phone data. The project addresses three goals.
The first one is the creation of research resources for large-scale behavioral modeling from mobile sensor data. Cell phones are rapidly becoming the ultimate sensor. Equipped with accelerometers, GPS, Bluetooth, in addition to communication and internet access capabilities, cell phones can ubiquitously trace individual and social activities for entire populations, and therefore are opening novel possibilities for research in several sciences. The second objetive of the project is the development of algorithms to robustly represent human behavior at the personal and group level, based on the integration of heterogeneous observation sources - location, motion, proximity, and communication. These behavioral descriptors will provide short-term snapshots of the physical and social pace of people's life. Finally, the third goal is the development of machine learning methods to automatically discover long-term personal routines (regularities in people's lives) and to discover and characterize groups from communication patterns, mutual proximity, and similar routines.
Overall, the project will design algorithms capable of answering behavioral questions that allow to build individually and socially meaningful mobile applications.
Partners
Idiap Research Institute, Principal Investigator
Nokia Research Center, Lausanne
