Improving Location Estimation with Two-Tier Particle Filtering in Mobile Wireless Environment

A particle filter is a sequential Monte Carlo method that is superior in estimating the state of a dynamic system under nonlinear/non-Gaussian circumstance. Due to its nature, a particle filter has been regarded as an appropriate algorithm for localization. However, conventional problems, such as sample impoverishment and degeneracy problem, have not been perfectly solved yet. To solve these problems in mobile wireless environment, we propose an enhanced localization scheme, called Gaussian kernel density estimation-based particle filtering (GKPF), which calculates the target distribution (for location estimation) based on nonparametric technique. In order to estimate the target distribution, the GKPF algorithm creates both unimodal and multimodal distributions based on particle representations, and it calculates a pdf for each distribution with Gaussian kernel-density estimation. Simulation study indicates that the proposed GKPE scheme can accurately estimate the location in mobile wireless environment.