Learning to Detect User Activity and Availability from a Variety of Sensor Data

  • Authors:
  • Martin Mühlenbrock;Oliver Brdiczka;Dave Snowdon;Jean-Luc Meunier

  • Affiliations:
  • -;-;-;-

  • Venue:
  • PERCOM '04 Proceedings of the Second IEEE International Conference on Pervasive Computing and Communications (PerCom'04)
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

Using a networked infrastructure of easily availablesensors and context-processing components, we aredeveloping applications for the support of workplaceinteractions. Notions of activity and availability arelearned from labeled sensor data based on a Bayesianapproach. The higher-level information on the users isthen automatically derived from low-level sensorinformation in order to facilitate informal ad hoccommunications between peer workers in an officeenvironment.