Optimization of Radio Frequency Identification Reference Tag Location Algorithm Based on Back Propagation Neural Network

In order to solve the problem that the received signal strength indicator (RSSI) is interfered by noise in radio frequency identification (RFID) signal strength localization algorithm, an optimization algorithm based on back propagation neural network (BPNN) is proposed. By establishing two BPNN models of signal strength, the algorithm corrects the RSSI values of the reference tag and the tag to be tested respectively, which reduces the interference error when the reader reads the RSSI value of the tag, and improves the positioning accuracy. The BPNN fitting model is applied to location identification based on dynamic active RFID calibration (LANDMARC) positioning algorithm and active RFID-based localization using virtual reference elimination (VIRE) positioning algorithm to carry out simulation experiments. The results show that the optimized algorithm can effectively improve the positioning performance such as positioning accuracy and positioning stability.