The COVID-19 pandemic has had an impact across the globe. This includes the many lives lost and the severe disruption to economies and daily lives. Researchers in a variety of fields have been motivated to use their expertise to help address the many challenges of this on-going pandemic. Communication and Networking researchers are among these. Communications and networking technologies can be utilized to help facilitate contact tracing and other forms of remote health monitoring. Epidemic models developed for studying the propagation of information and viruses in communication networks can be adapted to study the propagation of a true epidemic like COVID-19. Techniques such as machine learning can be utilized to make better predictions from limited public health data. Approaches for security and privacy can be leveraged to protect confidential health information. The goal of this special issue of the Journal of Communications and Networks is to highlight some of the work being done in these important areas.
From the submissions we have accepted 7 papers to appear in this issue.
The first paper, "Modeling COVID-19 with Mean Field Evolutionary Dynamics: Social Distancing and Seasonality," proposes mean field evolutionary dynamics (MFEDs) as a new approach for modeling the evolution of COVID-19. This approach is inspired by optimal transport theory and mean field games on graphs. This model is used to study the impact of one-time social distancing and seasonality through the post pandemic period.
The second paper, "Optimization of Resource-Constrained Policies for COVID-19 Testing and Quarantining," is motivated by the limited availability of PCR tests, which was especially acute during the early days of the pandemic. The authors provide a framework that utilizes a stochastic disease model and a "community graph" model to study different testing and quarantine policies.
The third paper, "Measuring the Impact of COVID-19 Restrictions on Mobility: A Real Case Study from Italy," performs data mining on a vehicular mobility dataset from Bologna, Italy during a period that includes the first lockdown phase in Italy. The analysis is used to study the impact of mobility restrictions on traffic flows.
The fourth paper, "Applying a Deep Learning Enhanced Public Warning System to Deal with COVID-19," is motivated by public warning systems that are used by some governments to quickly deliver information related to COVID-19. These systems broadcast text messages over cellular networks within a given area. The authors apply deep learning and Generative Adversarial Networks (GANs) to optimize the broadcast area to better target where messages are sent.
The fifth paper, "Privacy-preserving COVID-19 Contact Tracing using Blockchain," presents an approach for preserving use privacy when collecting information for contact tracing. Their approach utilizes homomorphic encryption and a permission-less blockchain network.
The sixth paper, "WeTrace: A Privacy-preserving Tracing Approach," presents an approach that utilizes the Bluetooth Low Energy (BLE) communication, Global Positioning System (GPS) and public-key cryptography for collecting user data that can be used for contact tracing while maintaining user privacy.
The seventh paper, "Energy Efficient Contact Tracing and Social Interaction based Patient Prediction System for COVID-19 Pandemic," also utilizes BLE and GPS for contact tracking. The focus of this paper is on developing an infection prediction algorithm that utilizes the collected data to determine the probability that a given user is infected and alert the user if their risk warrants this. Approaches for reducing the required energy of the proposed approach are also given.
We would like to thank all of the authors who submitted their work to this special issue. We are equally grateful to all reviewers, whose critical comments and suggestions contributed to the quality of this special issue. Finally, we want to acknowledge Grace Kim for her support throughout the process of preparing this special issue.