A highly accurate and scalable approach for addressing location uncertainty in asset tracking applications

Abstract

Tracking systems that use RFID are increasingly being used for monitoring the movement of goods in supply chains. While these systems are effective, they still have to overcome significant challenges, such as missing reads, to improve their performance further. In this paper, we describe an optimised tracking algorithm to predict the locations of objects in the presence of missed reads using particle filters. To achieve high location accuracy we develop a model that characterises the motion of objects in a supply chain. The model is also adaptable to the changing nature of a business such as flow of goods, path taken by goods through the supply chain, and sales volumes. A scalable tracking algorithm is achieved by an object compression technique, which also leads to a significant improvement in accuracy. The results of a detailed simulation study shows that our object compression technique yields high location accuracy (above 98% at 0.95 read rate) with significant reductions in execution time and memory usage.