Abstract
Recently, RSS fingerprint-based location has been considered as a low-complexity solution for indoor localization. However, constructing a fingerprint map requires a great amount of manual effort to achieve a high location accuracy. In this paper, we present a refinement method to reduce the necessary manual effort without degrading the location accuracy. This method transforms a coarse-gained fingerprint map containing only a small number of offline samples into a high-density fingerprint map by augmenting the map with artificial samples. In particular, a local-to-local strategy is proposed to improve the accuracy of artificial samples. Furthermore, we propose a judgment criterion to determine whether a fingerprint map should continue to be refined when it has reached a certain density and which refined fingerprint map can achieve the best location accuracy. Extensive experimental results show that our proposed method can significantly improve the location accuracy without additional manual effort compared with the original fingerprint map.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
