ISIL: Instant search-based indoor localization

As GPS signals may not be available indoor and can be blocked easily by obstacle, several localization techniques based on Wi-Fi have been proposed. Most of them require a pre-training step for known locations which is time-consuming and not practical for wide-scale deployment. This paper proposes an alternative approach for indoor localization based on the SSID of nearby access points (APs) at a specific location. The idea of this work is based on the observation that many AP´s names contain information related to the location. Thus, the observable APs´ names are mined via a search engine as a location indicator. The returned search results are analyzed and aggregated to predict the position of the location. Unlike existing localization algorithm, our approach is simple, yet requires no training time and is nearly independent of either Wi-Fi signals changes or mobile devices. To verify our approach, we conduct an experiment consisting of more than 3,000 locations spreading over 60,000 meters around Ho Chi Minh City (HCMC). This method can achieve an accuracy of up to 70 percent for exact address matching and up to 88 percent for nearby location with radius less than 100 meters.