Enhancing Cluster-based RFID Tag Localization using artificial neural networks and virtual reference tags

Abstract

Indoor/outdoor localization has gained importance as it has the potential to improve various processes related to the resource management of construction projects and to deliver personalized and location-based services (LBS). Radio Frequency Identification (RFID) based systems, have been widely used in different applications in construction and maintenance. This paper investigates the usage of active RFID technology for the localization of movable objects (e.g. material, equipment, tools, and assets) equipped with RFID tags using handheld readers. The method builds on Cluster-based Movable Tag Localization (CMTL) technique which uses k-Nearest Neighbor (k-NN) algorithm. CMTL uses multidimensional clustering technique that considers signal pattern similarity between target and reference tags together with spatial distribution of reference tags for detecting the region where the target tag is located. This paper proposes applying an irregular bilinear interpolation method to form a grid of virtual reference tags within the selected cluster of real reference tags. Moreover, the proposed method uses artificial neural networks (ANN) for positioning the target tag, as opposed to empirical weighted averaging formulas used in similar k-NN based methods. Comparative analysis is performed to quantify the improvement of the proposed method over similar k-NN-based methods using a simulation environment. A case study is performed to analyze the performance of the proposed method.