WiFiBoost: A terminal-based method for detection of indoor/outdoor places

Abstract

We present a binary classifier namedWiFiBoost which makes use of RSSIs from the existing 802.11 access points (AP) in order to infer whether a device is inside a building. Our weak learner is based on the feature of RSSI comparison between pairs of APs. The resulting model is really compact and efficient, and it can be stored in the mobile device. Our classifier also minimizes the negative effect of unpredicted AP failures or changes in the network infrastructure, which will result in a moderate impact on the classification error under those circumstances.