2016/10/06 by Rizanne Elbakly, Moustafa Youssef, Elbakly, Rizanne +1 · 1 citation
Engineering · Computer Science · #Indoor and Outdoor Localization Technologies #Energy Efficient Wireless Sensor Networks #Speech and Audio Processing
paper · pdf · doi:10.48550/arxiv.1610.02274
Accurate estimation of the confidence of an indoor localization system is\ncrucial for a number of applications including crowd-sensing applications,\nmap-matching services, and probabilistic location fusion techniques; all of\nwhich lead to an enhanced user experience. Current approaches for quantifying\nthe output accuracy of a localization system in real-time either do not provide\na distance metric, require an extensive training process, and/or are tailored\nto a specific localization system. In this paper, we present the design,\nimplementation, and evaluation of CONE: a novel calibration-free accurate\nconfidence estimation system that can work in real-time with any location\ndetermination system. CONE builds on a sound theoretical model that allows it\nto trade the required user confidence with tight bound on the estimated\nconfidence radius. We also introduce a new metric for evaluating confidence\nestimation systems that can capture new aspects of their performance.\nEvaluation of CONE on Android phones in a typical testbed using the iBeacons\nBLE technology with a side-by-side comparison with traditional confidence\nestimation techniques shows that CONE can achieve a consistent median absolute\nerror difference accuracy of less than 2.7m while estimating the user position\nmore than 80% of the time within the confidence circle. This is significantly\nbetter than the state-of-the-art confidence estimation systems that are\ntailored to the specific localization system in use. Moreover, CONE does not\nrequire any calibration and therefore provides a scalable and ubiquitous\nconfidence estimation system for pervasive applications.\n