| In recent years,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 realtime user location significantly improves the efficiency of advertising push process and brings broader profits.However,most of the Wi-Fi based indoor localization approaches requiring professionals to deploy expensive beacon devices.Besides,the signal acquisition process is both time-consuming and labor-intensive.Furthermore,the accuracy of the indoor localization algorithm based on crowdsourcing fingerprints is seriously affected by the fluctuation of the RSS,and the poor realtime localization performance caused by the heterogenetiy of the various intelligent terminal devices cannot be avoided.All of the above shortcomings severely limits the extensive promotion of related LB S applications.In response to the above disadvantages,this paper introduces a zero-cost shop-level indoor localization algorithm utilizing crowdsourcing fingerprints to obtain the shop recognition where the user is located.Naturally adopting the Wi-Fi,GPS,and time-stamp information collected from the smartphone when user paid in the store to construct the crowdsourcing fingerprint,the proposed algorithm avoids the requirement for the indoor map and get rid of both devices cost and manual signal collecting process.Moreover,a novel 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.At the same time,this paper 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 proposed algorithm achieves more than 93%localization accuracy. |
PDF Full Text Request