1-2hit |
This paper considers the problem of target location estimation in heterogeneous wireless sensor networks and proposes a novel algorithm using a factor graph to fuse the heterogeneous measured data. In the proposed algorithm, we map the problem of target location estimation to a factor graph framework and then use the sum-product algorithm to fuse the heterogeneous measured data so that heterogeneous sensors can collaborate to improve the accuracy of target location estimation. Simulation results indicate that the proposed algorithm provides high location estimation accuracy.
This paper considers the problem of target location estimation in a wireless sensor network based on IEEE 802.15.4 radio signals and proposes a novel implementation of the maximum likelihood (ML) location estimator based on the Cross-Entropy (CE) method. In the proposed CE method, the ML criterion is translated into a stochastic approximation problem which can be solved effectively. Simulations that compare the performance of a ML target estimation scheme employing the conventional Newton method and the conjugate gradient method are presented. The simulation results show that the proposed CE method provides higher location estimation accuracy throughout the sensor field.