Abstract
With the development of indoor localization technology, the location-based services such as product advertising recommendation in the shopping mall attract widespread attention, as precise user location significantly improves the efficiency of advertising push and brings broader profits. However, most of the Wi-Fi-based indoor localization approaches requiring professionals to deploy expensive beacon devices and intensively collect fingerprints in each location grid, which severely limits its extensive promotion. We introduce a zero-cost indoor localization algorithm utilizing crowdsourcing fingerprints to obtain the shop recognition where the user is located. Naturally utilizing the Wi-Fi, GPS, and time-stamp fingerprints collected from the smartphone when user paid as the crowdsourcing fingerprint, we avoid the requirement for indoor map and get rid of both devices cost and manual signal collecting process. Moreover, a shop-level hierarchical indoor localization framework is proposed, and high robustness features based on Wi-Fi sequences variation pattern in the same shop analysis are designed to avoid the received signal strength fluctuations. Besides, we also pay more attention to mine the popularity properties of shops and explore GPS features to improve localization accuracy in the Wi-Fi absence situation effectively. Massive experiments indicate that SP-Loc achieves more than 93% localization accuracy.
Highlights
With the development of mobile indoor localization technology, location-based services (LBSs) in the shopping malls have attracted widespread attention, the shop-level indoor localization in the shopping mall has become a new research hotspot, since shoplevel localization algorithm has a significant impact on the product advertising recommendation
In the construction phase of the fingerprint database, the Access Point (AP)-related equipment must be deployed by the professional staff, and the Wi-Fi signals are collected repeatedly in every location grid for lower measuring error, which leads to intensive manual labor and additional expensive devices expense with maintenance cost
Shop-level indoor localization algorithm based on crowdsourcing fingerprints without the indoor map
Summary
With the development of mobile indoor localization technology, location-based services (LBSs) in the shopping malls have attracted widespread attention, the shop-level indoor localization in the shopping mall has become a new research hotspot, since shoplevel localization algorithm has a significant impact on the product advertising recommendation. Further generate the feature vector of the collected signal as Wi-Fi fingerprinting to establish a fingerprint database; during the real-time positioning phase, users scan current Wi-Fi signal in the environment to match the feature vectors with the fingerprint database built in advance, so as to find the location of the highest similarity Wi-Fi fingerprint corresponding to the location of the user This approach achieves meter-level localization accuracy; since the auxiliary devices’ expense cost and labor-intensive deployment process,[1,2,3] the promotion of Wi-Fi-based indoor localization approach is severely limited. Along with the popularization of mobile payment technology, we naturally utilize the indoor Wi-Fi signals, GPS coordinates and time-stamps that smartphones collected when user pay in the shop, which effectively avoids the cost of deploying AP device and manual labor. We pay more attention to the variation pattern of APs and GPS coordinates aggregation characteristics in the shops to design novel features to obtain better localization performance
Sign-in/Register to view highlights & summary 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 callMore From: International Journal of Distributed Sensor Networks
Disclaimer: 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.
