A behavioral pattern adapted to individual for providing ubiquitous service in intelligent space
CIMMACS'06 Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics
RFID-based networks: exploiting diversity and redundancy
ACM SIGMOBILE Mobile Computing and Communications Review
A review of smart homes-Present state and future challenges
Computer Methods and Programs in Biomedicine
Correct behavior identification system in a Tagged World
Expert Systems with Applications: An International Journal
Detection of user mode shift in home
UCS'07 Proceedings of the 4th international conference on Ubiquitous computing systems
International Journal of Mobile Learning and Organisation
Developing mobile ubiquitous services for the elderly using virtual environments
BEBI'09 Proceedings of the 2nd WSEAS international conference on Biomedical electronics and biomedical informatics
Proceedings of the 6th Euro American Conference on Telematics and Information Systems
Hi-index | 0.00 |
There has been much research on user activityassistance applications using the location of users andobjects as context. However people's activities aredescribed in terms of time sequence aspect in addition tolocation aspect. Therefore, it is important for enhanceduser activity support systems to consider the user'scontext in terms of spatio-temporal constraints. In thispaper, we propose a user activity assistance system thatemploys a state sequence description scheme to describethe user's contexts. In this scheme, each state is describedas a spatio-temporal relationship between the user andobjects in the real world. Typical sets of states are storedas models of tasks performed by a user. To try out thissystem, we have developed an experimental housecontaining various embedded sensors and RFID-taggedobjects. Each state is detected by a decision treeconstructed by a C4.5 algorithm using the output of thesensors and the RFID tags. The user's context is obtainedby matching the detected state series to a task model.Having evaluated the performance of the proposed systemin this experimental house, we conclude that our system isan effective way of acquiring the user's spatio-temporalcontext.