An RFID Data and Location Parameter Joint Estimation Based on an Improved MCMC Method

Abstract

The location parameter of the electronic tag is the necessary condition for RFID application systems to realize their operation functions. Based on RFID detection model within which the target of the symbol location will spill over to adjacent area when sampling, the posterior probability distribution of the parameters to be estimated is obtained from the conditional likelihood function and the prior distribution of unknown parameters by Bayesian theory. Metropolis-Hastings (M-H) sampling algorithm of Markov Chain Monte Carlo (MCMC) is used to jointly estimate the RFID data and tag symbol location parameter within the range of multiple readers, and in this paper, the M-H sampling is improved by considering the prior knowledge and constraints. At last, the experimental results, using large simulated data, demonstrate the accuracy and efficiency of the proposed algorithm