A Spatio-GraphNet Model for Real-time Contact Tracing of CoVID-19 Infection in Resource Limited Settings

Abstract

Placing contact tracing tool in the hands of all is certain to enhance contact identification-as individuals can perform self-tests to discover in real-time, frequently associated contacts, ultimately instilling caution and adherence to recommended local and international guidelines. It can also assist epidemiologists and policymakers to formulate appropriate policies as well as proffer cost-effective solution for containing disease outbreaks. A Spatio-GraphNet model for real-time contact tracing of CoVID-19 infection is proposed in this paper for real-time crowd source of contacts-using a WiFi-like soft-robot enabled on mobile phones. Once enabled, useful contact tracing parameters can be captured and stored. Using knowledge of Graph Theory, production traces of stored contacts are filtered for efficient contact tracing, practical disease surveillance and prompt medical/healthcare intervention. Simulation results reveal the contact tracing dashboard with appropriate parameters thresholds, application and evaluation of various statistical kernels as well as practical implications of the study.