Locater

Abstract

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 (APs), 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 tasks - 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. LOCATER uses a bootstrapping semi-supervised learning method for coarse localization and a probabilistic method to achieve finer localization. The paper shows that LOCATER can achieve significantly high accuracy at both the coarse and fine levels.

Data Imputation for Sparse Radio Maps in Indoor Positioning (Extended Version)

“…Missing values in these studies are identifiers of sensors such as RFID readers. In addition, Lin et al [38] propose a semi-supervised scheme to detect and impute missing AP identifiers in raw Wi-Fi connectivity data. Our work differs from these works in that we aim to impute numerical values instead of AP or RFID reader identifiers.…”

“…While a variety of indoor positioning technologies exist, positioning based on Wi-Fi fingerprinting [26] is popular: the ubiquity of Wi-Fi enables positioning without the deployment of additional expensive infrastructure, and the technology is non-intrusive to users. However, the accuracy of Wi-Fi fingerprinting based positioning depends heavily on the quality of the radio map data used [38], [46], [52], [55].…”

PlanIoT: A Framework for Adaptive Data Flow Management in IoT-enhanced Spaces

“…In particular, as depicted in Fig. 2, the IoT space specification and Application QoS requirements subcomponents are used to compose the IoT system specification that represents the overall Edge infrastructure of a smart space in a structured way 1 . The specification includes information related to the (i) IoT devices: average message sizes, frequency (e.g., periodic, event-driven) as well as the space properties (e.g., temperature of a room); (ii) IoT applications: number of applications deployed, their category, their topic-based subscription filters, and their QoS requirements; and the (iii) Edge broker: the available network resources and the system capacity.…”

“…Serving applications falling to these types may require a tsunami of data that keeps growing. For instance, an occupancy monitoring application deployed in a large university campus (with over 200 buildings) must process WIFI connectivity data in the order of millions each day [1]. In addition, bandwidth and data-intensive applications such as EM and VS affect the performance of all applications.…”

Cloud-based Indoor Positioning Platform for Context-adaptivity in GNSS-denied Scenarios

“…Lin, Jiang, Yus, Bouloukakis, Chio, Mehrotra, and Venkatasubramanian [173], for example, proposed a new three-step method: rstly, unlabelled data is completed using additional measurements. Secondly, the coarse localisation is carried out, and, nally, the ne location is estimated using a probabilistic model.…”