Determining location of mobile device using sensor space to physical space mapping

Abstract

A mobile device can identify its physical location without explicit knowledge of physical coordinates, but instead using sensor measurements dependence on distance, e.g., signal strength from a Wi-Fi router. Sensor measurements can be used to determine the mobile device is at a same physical location as a previous measurement. For example, numerous measurements of sensor values can form data points that are clustered in sensor space, where a cluster of data points in sensor space corresponds to a physical cluster of physical positions in physical space. A current physical location of the mobile device can be determined by identifying which cluster of sensor positions the current measurements correspond. To identify the cluster of sensor positions, a probability can be determined for each cluster based on a sensor distance between the current measurement and a representative data point of the cluster and a kernel function.