A Bayes Decision Model for RSS Based Location Estimation

Abstract

This work introduces a location estimation method based on Bayes decision theory using radio signal strengths for indoor environment. Signal strengths are observed through three transmitters at three distinct frequencies in UHF band, an active RFID tag and a modem connected to a computer. The test environment is 2100 cm × 720 cm, which is divided into classed of square grids. For each class, a set of received signal strengths are measured and processed. Assuming that the class in which the RFID lag was located in the previous time of measurement is known, the next location (class) is estimated using Bayes decision theory. Proposed method is tested in a laboratory environment with obstacles. Results show that proposed method will be successful in location estimation where the estimation error stays within around 2 m.