Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services

TL;DR

GEM is a semi-supervised geofencing system that uses ambient RF signals and a novel bipartite network embedding algorithm to accurately detect whether a user is inside a predefined area, with continuous learning capabilities.

Contribution

The paper introduces BiSAGE, a new bipartite graph neural network embedding method, and applies it within GEM for improved RF-based geofencing accuracy.

Findings

GEM achieves up to 34% higher F-score compared to existing methods.

BiSAGE improves F-score by 54% over non-BiSAGE approaches.

GEM demonstrates state-of-the-art performance across diverse environments.

Abstract

In applications such as elderly care, dementia anti-wandering and pandemic control, it is important to ensure that people are within a predefined area for their safety and well-being. We propose GEM, a practical, semi-supervised Geofencing system with network EMbedding, which is based only on ambient radio frequency (RF) signals. GEM models measured RF signal records as a weighted bipartite graph. With access points on one side and signal records on the other, it is able to precisely capture the relationships between signal records. GEM then learns node embeddings from the graph via a novel bipartite network embedding algorithm called BiSAGE, based on a Bipartite graph neural network with a novel bi-level SAmple and aggreGatE mechanism and non-uniform neighborhood sampling. Using the learned embeddings, GEM finally builds a one-class classification model via an enhanced histogram-based algorithm for in-out detection, i.e., to detect whether the user is inside the area or not. This model also keeps on improving with newly collected signal records. We demonstrate through extensive experiments in diverse environments that GEM shows state-of-the-art performance with up to 34% improvement in F-score. BiSAGE in GEM leads to a 54% improvement in F-score, as compared to the one without BiSAGE.