The current COVID-19 epidemic have transformed every aspect of our lives, especially our behavior and routines. These changes have been drastically impacting the economy in each region, such as local restaurants and transportation systems. With massive amounts of ambient data being collected everywhere, we now can develop innovative algorithms to have a much greater understanding of epidemic spread patterns of COVID-19 based on spatiotemporal data. The findings will open up the possibility to design adaptive planning or scheduling systems that will help preventing the spread of COVID-19 and other infectious diseases.
In this tutorial, we will review the trending state-of-theart machine learning techniques to model epidemic spread patterns with spatiotemporal data. These techniques are organized from two aspects: (1) providing a comprehensive review of recent studies about human routine behavior modeling, such as inverse reinforcement learning and graph neural network, and the impacts of behaviors on the spread patterns of infectious diseases based on GPS data; (2) introducing the existing literature on using remote sensing data to monitor the spatiotemporal pattern of the epidemic spread. Under current epidemic with unknown lasting time, we believe that modeling the spread patterns of COVID-19 epidemic is an important topic that will benefit to researchers and practitioners from both academia and industry.
Lin, B. and Jia, X., Chen, Z. 2021 Studying Spread Patterns of COVID-19 based on Spatiotemporal Data SIAM International Conference on Data Mining (SDM) Tutorial.
SIAM International Conference on Data Mining (SDM) Tutorial
© 2022 by SIAM