Approximation capabilities of multilayer feedforward networks
Neural Networks
The active badge location system
ACM Transactions on Information Systems (TOIS)
Communication systems engineering
Communication systems engineering
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
A Probabilistic Room Location Service for Wireless Networked Environments
UbiComp '01 Proceedings of the 3rd international conference on Ubiquitous Computing
Tutorial on location determination by RF means
MELT'09 Proceedings of the 2nd international conference on Mobile entity localization and tracking in GPS-less environments
| Hi-index | 0.00 |
The objective of this work is to estimate the locations of Bluetooth enabled devices. Collecting received signal strength from a device may help with estimating its location. However, for indoor environments, the signal attenuation model becomes complex and difficult to represent concisely due to multi-path and small-scale fading effects. The flexible modeling and learning capabilities of neural networks provide lower errors in determining the position even in the presence of these destructive effects. A standard backpropagation learning algorithm was employed to minimize the error between target and estimated locations in order to find the weights of the links of the neural network. Simulation results show that a neural network with three input units and 8 hidden layer units and two output units can provide 75cm root mean square (RMS) error.