Big Data Intelligence Solution for Health Analytics of COVID-19 Data with Spatial Hierarchy
Carson K. Leung, Chenru Zhao
Abstract
In the current era of big data, technological advancements have made it easy and quick to generate and collect huge volumes of varieties of data from wide ranges of rich data sources. These big data may be of different levels of veracity, including precise data and imprecise or uncertain data. Embedded in the data are valuable information and useful knowledge that can be discovered by big data intelligence and computing. In this paper, we propose a big data intelligence solution for health analytics with spatial hierarchy. In particular, we focus on analyzing coronavirus disease 2019 (COVID-19) epidemiological data at different spatial granularity levels. Since its outbreak, there have been cumulatively millions of COVID-19 cases observed in various spatial locations around the world. Our solution focuses on analyzing and mining valuable information and useful knowledge (e.g., distribution, frequency, patterns) of health-related states and characteristics in populations in various spatial locations in a top-down fashion along the spatial hierarchy. To reduce redundancy, our solution discovers and returns to users (e.g., researcher, civilian) new information and knowledge not found at previous spatial hierarchical levels. The discovered information and knowledge helps the users to understand the disease better, and thus take an active role to fight, control, and/or combat the disease. Evaluation of our big data intelligence solution on real-life COVID-19 data demonstrates its practicality in health analytics of the data with spatial hierarchy and in revealing new knowledge about COVID-19 cases at different spatial granularity levels. The solution is expected to be adaptable to health analytics of other diseases.