Inferring proximity from Bluetooth Low Energy RSSI with Unscented Kalman Smoothers
This work addresses the challenge of accurate proximity detection for Covid-19 contact tracing apps, which is crucial for public health but is incremental as it builds on existing state-space modeling techniques.
The paper tackled the problem of inferring proximity from Bluetooth Low Energy RSSI signals, which are noisy and variable, by using an Unscented Kalman Smoother with Gaussian process transforms to model distance probabilities. The results showed that this method outperformed traditional classification approaches in risk prediction, achieving good performance in linear time on real-world datasets.
The Covid-19 pandemic has resulted in a variety of approaches for managing infection outbreaks in international populations. One example is mobile phone applications, which attempt to alert infected individuals and their contacts by automatically inferring two key components of infection risk: the proximity to an individual who may be infected, and the duration of proximity. The former component, proximity, relies on Bluetooth Low Energy (BLE) Received Signal Strength Indicator(RSSI) as a distance sensor, and this has been shown to be problematic; not least because of unpredictable variations caused by different device types, device location on-body, device orientation, the local environment and the general noise associated with radio frequency propagation. In this paper, we present an approach that infers posterior probabilities over distance given sequences of RSSI values. Using a single-dimensional Unscented Kalman Smoother (UKS) for non-linear state space modelling, we outline several Gaussian process observation transforms, including: a generative model that directly captures sources of variation; and a discriminative model that learns a suitable observation function from training data using both distance and infection risk as optimisation objective functions. Our results show that good risk prediction can be achieved in $\mathcal{O}(n)$ time on real-world data sets, with the UKS outperforming more traditional classification methods learned from the same training data.