Crowdsourcing based terminal positioning using multidimensional data clustering and interpolation

Recent years can be characterized by the rapid increase of mobile device usage in people's lives. Contemporary mobile devices are equipped with many sensors and have high computational and processing capabilities. In a crowdsourcing systems, mobile users participate constructively in specific information handling. Data collected by crowd of mobile devices and stored in a database may help offering new services such as operator's radio quality evaluation and tracking of users. In this paper, we focus on mobile positioning by clustering and interpolating data to match fingerprints to positions. Our method is trained during the offline phase and parameters are periodically updated to track possible changes in propagation environment.