Hypothesis Testing Based Model for Fingerprinting Localization Algorithms

Despite the popularity of Fingerprinting Localization Algorithms (FPS), general theoretical frameworks for their performance studies have rarely been discussed in the literature. In this work, after setting up an abstract model for the FPS, we show that a fingerprinting-based localization problem can be cast as a Hypothesis Testing (HT) problem and therefore various results from the HT literature can be used to provide insights, guidelines, and performance bounds for the FPS. This includes the scaling limits of error probability in terms of the number of measurements and the precise characterization of localization error. The provided results hold for the general FPS. Additionally, Received Signal Strength (RSS)-based fingerprinting algorithms are particularly considered from the theoretical viewpoint due to their widespread practical usage. Simulations and experimental results characterize numerically the findings of the theoretical framework and demonstrate its consistency with realistic localization scenarios.