The anatomy of a context-aware application
MobiCom '99 Proceedings of the 5th annual ACM/IEEE international conference on Mobile computing and networking
The Cricket location-support system
MobiCom '00 Proceedings of the 6th annual international conference on Mobile computing and networking
Multi-Camera Multi-Person Tracking for EasyLiving
VS '00 Proceedings of the Third IEEE International Workshop on Visual Surveillance (VS'2000)
Hi-index | 0.00 |
The problem of user location estimation using the receiving signal strength in a radio-frequency wireless local area network (WLAN) is discussed in this paper. Instead of taking the physical properties of the signal propagation int o account directly, an method based on a machine learning framework is presented. This method employs a multivariable Gauss distribution model and consists of an offline training phase and a real time locating phase. In the offline phase the received signal strength of many training locations are recorded and the parameters of the Gauss distribution are calculated, and in the real time phase a user location is determined by matching the received signal strength patterns against the training patterns. Experiments demonstrate that the proposed method has lower locating errors and is feasible to locate user in a WLAN.