DISTERNING: Distance Estimation Using Machine Learning Approach for COVID-19 Contact Tracing and Beyond

Abstract

Since the coronavirus disease 19 (COVID-19) outbreak, the epidemiological analysis has raised a strong requirement for more effective and accurate contact tracing solution. However, the existing contact tracing solutions either lacked the evaluation of tracing proximity or the features used for the tracing proximity evaluation were susceptible to certain negative environmental factors (e.g., body shielding). In this article, we propose a novel distance estimation algorithm based on machine learning for contact tracing: DISTERNING, where we leverage machine learning algorithms including Learning Vector Quantization, Regression, and Deep Feed-forward (DFF) Neural Network, data processing methods, and digital filters to process the Bluetooth signal information collected by the mobile phone for contact distance estimation. A contact tracing scheme based on edge computing is also proposed for algorithm deployment due to the requirements of the computational power. Compared with the existing contact tracing solutions, our algorithm considers the factors that have significant negative influence on the Bluetooth signal for distance estimation in reality. The evaluation results show that when the collected Bluetooth signal is influenced by real-world negative environmental factors, employing our proposed algorithm DISTERNING can keep the accuracy of the estimated distance reliable. The output distance can be combined with some medical models to conduct infection risk assessments.