Wi-Fi based fingerprinting systems, mostly utilize the Received Signal Strength Indicator (RSSI), which is known to be unreliable due to environmental and hardware effects. In this paper, we present a novel Wi-Fi fingerprinting system, exploiting the fine-grained information known as Channel State Information (CSI). The frequency diversity of CSI can be effectively utilized to represent a location in both frequency and spatial domain resulting in more accurate indoor localization. We propose a novel location signature CSI-MIMO that incorporates Multiple Input Multiple Output (MIMO) information and use both the magnitude and the phase of CSI of each sub-carrier. We experimentally evaluate the performance of CSI-MIMO fingerprinting using the k-nearest neighbor and the Bayes algorithm. The accuracy of the proposed CSI-MIMO is compared with Finegrained Indoor Fingerprinting System (FIFS) and a simple CSI-based system. The experimental result shows an accuracy improvement of 57% over FIFS with an accuracy of 0.95 meters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.