A user context estimation method in the ubiquitous environment using acceleration sensor and RFID

Numerous studies of ubiquitous environments have been undertaken recently because of rapid development of computer and sensor technologies. This study examines a method for users’ context estimation in a ubiquitous environment. Position information of objects is managed using RFID tags and readers. Users’ context estimation uses feature vectors extracted from time series data obtained from acceleration sensors attached to the user; the vectors are combined with reading of the tags for analyses. We create a C4.5 decision tree using information described above and discuss the user context estimation method herein. Furthermore, we evaluate its feasibility using prototype system experiments.