A Machine Learning Approach to Digital Contact Tracing: TC4TL Challenge

TL;DR

This paper develops machine learning models using Bluetooth data and sensor features to improve digital contact tracing accuracy, significantly outperforming previous methods.

Contribution

It introduces a novel application of TableNet architecture and feature engineering for contact distance estimation, advancing the state of the art.

Findings

Total nDCF reduced from 2.08 to 0.21

Significant performance improvement over existing models

Effective use of Bluetooth and sensor data for contact estimation

Abstract

Contact tracing is a method used by public health organisations to try prevent the spread of infectious diseases in the community. Traditionally performed by manual contact tracers, more recently the use of apps have been considered utilising phone sensor data to determine the distance between two phones. In this paper, we investigate the development of machine learning approaches to determine the distance between two mobile phone devices using Bluetooth Low Energy, sensory data and meta data. We use TableNet architecture and feature engineering to improve on the existing state of the art (total nDCF 0.21 vs 2.08), significantly outperforming existing models.