A modified particle filter through Kullback-Leibler distance based on received signal strength

In this paper, we focus on the target tracking in wireless sensor network based on Received Signal Strength (RSS). The tracking via particle filter technique is enhanced by improving the effect of the RSS variations. We propose a modified Particle Filter (PF) that finding the optimal bound error for Kullback-Leibler Distance (KLD)-resampling algorithm to ameliorate the effect of the RSS variations by generating a sample set near the high-likelihood region. The key problem of this method is to determine bound error values for the resample-based approximation to minimize both the Root Mean Square Error (RMSE) and the number of particles used. By combining the new finding bound error with KLD-resampling, our experiments show that the new technique not only enhances the estimation accuracy but also improves the efficient number of particles compared with the traditional methods.