PROJECT TITLE :
Robust Urban Wireless Localization: Synergy Between Data Fusion, Modeling and Intelligent Estimation
In this paper, we tend to present a viable Bayesian estimation various to mobile localization enhancement in mixed line-of-sight (LOS)/non-LOS (NLOS) urban areas. The development of the proposed approach depends on a synergistic combination of valid mixture measurements, NLOS bias modeling and estimation, and computational intelligence. For reliable wireless positioning, we first introduce valid vary measurements in that the effect of the NLOS vary bias due to small-/giant-scale multipath fading is restricted. Subsequently, we propose a hybrid system framework with Markovian state transitions, knowledge fusion of valid vary and signal power, NLOS bias modeling, and fuzzy inferences for modeling the dynamics of a mobile station (MS) with respect to each base station (BS). The proposed framework enables us to develop a selective fuzzy-tuned extended Kalman filtering primarily based interacting multiple-model (SFT-IMM-EKF) algorithm for every BS to perform mobile location estimation. We tend to show that thanks to the synergistic effects, the proposed SFT-IMM-EKF can remarkably improve the IMM, the SFT-IMM and also the IMM-EKF. The result is substantiated by numerical simulations. As well, it's demonstrated that the proposed algorithm will robustly leverage against the adverse impacts of severe NLOS errors and MS mobility variations.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here