Abstract-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 zero-calibration 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 have deployed IncVoronoi on different Android phones using the iBeacons technology in a university campus. Evaluation of IncVoronoi with a side-by-side comparison with traditional fingerprinting techniques shows that it can achieve a consistent median accuracy of 2.8m under different scenarios with a low beacon density of one beacon every 44m2 . Compared to fingerprinting techniques, whose accuracy degrades by at least 156%, 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.

No abstract

Due to the recent proliferation of location-based services indoors, the need for an accurate floor estimation technique that is easy to deploy in any typical multi-story building is higher than ever. Current approaches that attempt to solve the floor localization problem include sensor-based systems and 3D fingerprinting. Nevertheless, these systems incur high deployment and maintenance overhead, suffer from sensor drift and calibration issues, and/or are not available to all users. In this paper, we propose StoryTeller, a deep learning-based technique for floor prediction in multi-story buildings. StoryTeller leverages the ubiquitous WiFi signals to generate images that are input to a Convolutional Neural Network (CNN) which is trained to predict loors based on detected patterns in visible WiFi scans. Input images are created such that they capture the current WiFi-scan in an AP-independent manner. In addition, a novel virtual building concept is used to normalize the information in order to make them building-independent. This allows StoryTeller to reuse a trained network for a completely new building, significantly reducing the deployment overhead. We have implemented and evaluated StoryTeller using three different buildings with a side-by-side comparison with the state-of-the-art floor estimation techniques. The results show that StoryTeller can estimate the user's floor at least 98.3% within one floor of the actual ground truth floor. This accuracy is consistent across the different testbeds and for scenarios where the models used were trained in a completely different building than the tested building. This highlights StoryTeller's ability to generalize to new buildings and its promise as a scalable, low-overhead, high-accuracy floor localization system.

A ubiquitous outdoor localization system that is easy to deploy and works equally well for all mobile devices is highly-desirable. The GPS, despite its high accuracy, cannot be reliably used for this purpose since it is not available on low-end phones nor in areas with low satellite coverage. The application of classical fingerprinting approaches, on the other hand, is prohibited by excessive maintenance and deployment costs.In this paper, we propose Crescendo, a cellular network-based outdoor localization system that does not require calibration or infrastructure support. Crescendo builds on techniques borrowed from computational geometry to estimate the user's location. Specifically, given the network cells heard by the mobile device it leverages the Voronoi diagram of the network sites to provide an initial ambiguity area and incrementally reduces this area by leveraging pairwise site comparisons and visible cell information.Evaluation of Crescendo in both an urban and a rural area using real data shows median accuracies of 152m and 224m, respectively. This is an improvement over classical techniques by at least 18% and 15%, respectively.

Floor localization is an integral part of indoor localization systems that are deployed in any typical high-rise building. Nevertheless, while many efforts have been made to detect floor change events leveraging phone-embedded sensors, there are still a number of pitfalls that need to be overcome to provide robust and accurate localization in the 3D space. In this paper, we present HyRise: a robust and ubiquitous probabilistic crowdsourcing-based floor determination system. HyRise is a hybrid system that combines the barometer sensor and the ubiquitous Wi-Fi access points installed in the building into a probabilistic framework to identify the user's floor. In particular, HyRise incorporates a discrete Markov localization algorithm where the motion model is based on the vertical transitions detected from the sampled pressure readings and the observation model is based on the overheard Wi-Fi access points (APs) to find the most probable floor of the user. HyRise also has provisions to handle practical deployment issues including handling the inherent drift in the barometer readings, the noisy wireless environment, heterogeneous devices, among others. HyRise is implemented on Android phones and evaluated using three different testbeds: a campus building, a shopping mall, and a residential building with different floorplan layouts and APs densities. The results show that HyRise can identify the exact user's floor correctly in 93%, 92% and 77% of the cases for the campus building, the shopping mall, and the more challenging residential building; respectively. In addition, it can identify the floor with at most 1-floor error in 100% of the cases for all three testbeds. Moreover, the floor localization accuracy outperforms that achieved by other state-of-the-art techniques by at least 79% and up to 278%. This accuracy is achieved with no training overhead, is robust to the different user devices, and is consistent in buildings with different structures and APs densities.