A Study On The Impact Of Indoor Positioning Performance On Activity Recognition Applications

Due to substantial research in indoor positioning a vast amount of location technologies and algorithms are available to enable various applications. However, it is challenging knowing which positioning system is optimal, or sufficient, for a specific application not only when considering development and maintenance costs, but also the potential impact of the positioning system's performance on the respective application's performance.In this paper, we present an evaluation of how positioning performance in various system setups affects two chosen real-world applications at a 160, 000m(2) hospital building complex using an existing WiFi system as primary sensing infrastructure. While a multitude of positioning applications are run at the hospital, we focused on two applications within human activity recognition (HAR). HAR is an application area of positioning where the impacts are indirect and challenging to predict, therefore motivating this type of investigation yet underrepresented in the literature.Our evaluation includes several WiFi based indoor positioning system variants, with different accuracies, and investigates the impact of their respective performances on the two HAR applications. Among others, our evaluation shows that positioning accuracy, as measured traditionally, is not the only performance measure important to consider, and that it has a surprisingly small impact on the applications' performance suggesting that the increased costs for a higher-accuracy positioning system often do not yield the anticipated returns.