LOCATER: Cleaning WiFi Connectivity Datasets for Semantic Localization
This paper explores the data cleaning challenges that arise in using WiFi connectivity data to locate users to semantic indoor locations such as buildings, regions, rooms. WiFi connectivity data consists of sporadic connections between devices and nearby WiFi access points, each of which may cover a relatively large area within a building. Our system, entitled semantic LOCATion cleanER (LOCATER), postulates semantic localization as a series of data cleaning challenges - first, it treats the problem of determining the AP to which a device is connected between any two of its connection events as a missing value detection and repair problem. It then associates the device with the semantic subregion (e.g., a conference room in the region) by postulating it as a location disambiguation problem. We propose a bootstrapping semi-supervised learning method for the coarse localization and probabilistic method to achieve finer localization. We show that LOCATER can achieve significantly high accuracy at both the coarse and fine levels. LOCATER offers several benefits over traditional indoor localization approaches since it neither requires active cooperation from users (e.g., downloading code on a mobile device and communicating with the server) nor installing external hardware (e.g., network monitors).
READ FULL TEXT