RFID indoor positioning algorithm based on asynchronous dominant action evaluation

Abstract

The invention relates to an RFID indoor positioning algorithm based on asynchronous dominant action evaluation. The signal strength value of the positioning target is used as input data, a global action network and a global evaluation network are established, and multiple thread sub-action networks and thread sub-evaluation networks are established. Multiple threads learn in parallel without interfering with each other, and then asynchronously update the learned experience to the global network. The global network finally outputs the specific position of the reference label, and obtains the asynchronous superior action evaluation and positioning model; when the target to be tested enters the detection area, The positioning model automatically predicts the exact location of the target. Since the indoor positioning action is continuous, the asynchronous superior action evaluation method is combined with RFID indoor positioning, which solves the positioning continuity problem well, and effectively solves the problems of long training time of indoor positioning model, low positioning accuracy and environmental noise impact. It is especially suitable for a large number of positioning targets.

Description

technical field [0001] The invention relates to an indoor positioning technology in wireless identification, in particular to an RFID indoor positioning algorithm based on asynchronous dominant action evaluation. Background technique [0002] In recent years, with the increasing demand for spatial location information, positioning technology has attracted more and more people's attention, especially the services that provide location information based on GPS positioning system, mobile Internet, smart phones and other technologies. Life brings great convenience. Outdoors without obstacles, GPS technology is relatively mature and widely used. However, due to obstacles such as buildings, plants, walls, etc., which can weaken or disperse the GPS signal, the GPS cannot be positioned. Therefore, the positioning system has also developed from outdoor positioning to indoor positioning. [0003] The existing indoor positioning methods are mainly based on ranging and non-ranging. T...

AI Technical Summary

Problems solved by technology

This method reduces the average positioning error by screening out high-quality RSSI values. However, the Bayesian algorithm is based on the assumption that the conditions are independent of each other. In practice, the features cannot be absolutely independent, which affects the actual positioning effect.

Images