A Mathematical Model for Fingerprinting-based Localization Algorithms (1610.07636v2)

Abstract: A general theoretical framework for Fingerprinting Localization Algorithms (FPS), given their popularity, can be utilized for their performance studies. In this work, after setting up an abstract model for FPS, it is shown that fingerprinting-based localization problem can be cast as a hypothesis testing (HT) problem and therefore various results in HT literature can be used to provide insights, guidelines and performance bounds for general FPS. This framework results in characterization of scaling limits of localization reliability in terms of number of measurements and other environmental parameters. It is suggested that Kullback-Leibler (KL) divergence between probability distributions of selected feature for fingerprinting at different locations encapsulates information about both accuracy and latency and can be used as a central performance metric for studying FPS. Although developed for an arbitrary fingerprint, the framework is particularly used for studying simple Received Signal Strength (RSS)- based algorithm. The effect of various parameters on the performance of fingerprinting algorithms is discussed, which includes path loss and fading characteristics, number of measurements at each point, number of anchors and their position, and placement of training points. Representative simulations and experimentation are used to verify validity of the theoretical frameworks in realistic setups.