Search

Due to the noisy indoor radio propagation channel, radio frequency (RF)-based location determination systems usually require a tedious calibration phase to construct an RF fingerprint of the area of interest. This fingerprint varies with the used mobile device, changes of the transmit power of smart access points (APs), and dynamic changes in the environment; requiring re-calibration of the area of interest; which reduces the technology ease of use. In this paper, we present IncVoronoi: a novel system that can provide low-overhead accurate RF-based indoor localization that works in realistic environments. The basic idea is that the relative relation between the received signal strength from two APs at a certain location reflects the relative distance from this location to the respective APs. Building on this, IncVoronoi incrementally reduces the user ambiguity region based on refining the Voronoi tessellation of the area of interest. IncVoronoi also includes a number of modules to efficiently run in realtime as well as to handle practical deployment issues including the noisy wireless environment, obstacles in the environment, heterogeneous devices hardware, and smart APs. We analyze the complexity of IncVoronoi and further deploy it on different Android phones using the iBeacons and WiFi technologies in a university campus and a commercial building. Evaluation of IncVoronoi with a side-by-side comparison with traditional fingerprinting techniques shows that it can achieve a consistent median accuracy less than 1.9m under different scenarios with a low beacon density of one beacon every 22m $^2$ 2 . Compared to fingerprinting techniques, whose accuracy degrades by at least 156 percent, this accuracy comes with no training overhead and is robust to the different user devices, different transmit powers, and over temporal changes in the environment. This highlights the promise of IncVoronoi as a next generation indoor localization system. [ABSTRACT FROM AUTHOR]

WiFi-based indoor localization systems are popular due to the WiFi ubiquity and availability in commodity smartphone devices for network communication. The majority of these systems focus on finding the user’s 2-D location in a single floor. However, this is of little value when the altitude of the user is unknown in any typical multi-story building. In this paper, we proposeTrueStory: a system that can accurately and robustly identify the user’s floor level using the building’s WiFi networks.TrueStorytargets challenging environments where the access point (AP) density is not uniform and/or there are open areas that make the APs heard strongly in faraway floors. To handle these challenges,TrueStoryemploys a number of techniques including signal normalization, AP power equalization, and fusing various learners using a multilayer perceptron neural network. We present the design and implementation ofTrueStoryand evaluate its performance in three different testbeds. Our evaluation shows thatTrueStorycan accurately identify the user’s exact floor level up to 91.8% of the time and within one floor error 99% of the time. This improves the floor estimation accuracy over the state-of-the-art systems and reduces the high floor errors by more than 23%. In addition, we show that it has a robust performance for various challenging environments. [ABSTRACT FROM AUTHOR]