Area Classification for RF Signals: A Graph Neural Network Approach

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Area Classification for RF Signals: A Graph Neural Network Approach"

By

Mr. Weipeng ZHUO


Abstract:

We study the problem of area classification for radio frequency (RF) signals,
where ambient RF signals, sampled by mobile Internet of Things (IoT) devices of
unknown locations, are to be identified by the areas they are collected. The
solutions to the problem are applied in geofencing (for in-out area detection)
and floor identification (for indoor localization) tasks. We consider the
general but challenging scenario where the RF signals may exhibit significant
spatial and temporal heterogeneities. By modelling the heterogeneous RF signals
as a bipartite graph, we develop novel efficient graph neural network (GNN)
approaches for the tasks.

In geofencing, the ambient RF signals of a geofencing area is first collected
for offline training. In online process, the system would detect in real time
whether the signals, as collected and reported by a wearable attached to a
user, are outside the area or not. We propose GEM, a geofencing approach based
on network embedding for offline training and online detection. GEM efficiently
processes the RF signals using a novel GNN called BiSAGE, and captures the
multi-modal signal distribution within the area based on an enhanced
histogram-based classification model. Extensive experimental results show that
GEM outperforms state-of-the-art algorithms significantly (by up to 34% in
F-score).

For floor identification, we first consider the case where RF signals weakly
spill over across floors (e.g., office buildings). A large number of signals
are crowdsourced from users, and only a small number of them are labelled with
their floor numbers. We propose GRAFICS, a graph embedding-based floor
identification system for the unlabelled signals. GRAFICS integrates a novel
graph embedding algorithm E-LINE to capture the signal relationship and to
efficiently classify the signals into different floors. It achieves higher than
96% in F-score with much fewer labelled signals per floor as compared with
other advanced.

For floor identification with more substantial signal spillover (e.g., shopping
malls), we propose FIS-ONE, a novel floor identification system that requires
only one labelled signal sample. FIS-ONE groups RF signals into different
clusters using our proposed RF-GNN, and then indexes the clusters with floor
numbers given the one labelled sample using a travelling salesman problem
formulation. Our extensive experiments demonstrates that FIS-ONE outperforms
other state-of-the-art algorithms substantially.


Date:                   Friday, 1 December 2023

Time:                   10:00am - 12:00noon

Venue:                  Room 4504
                        Lifts 25/26

Chairman:               Prof. Dan TSANG (CIVL)

Committee Members:      Prof. Gary CHAN (Supervisor)
                        Prof. Andrew HORNER
                        Prof. Pedro SANDER
                        Prof. Xueqing ZHANG (CIVL)
                        Prof. Carlee JOE-WONG (Carnegie Mellon University)


**** ALL are Welcome ****