ABSTRACT
Due to the COVID-19 pandemic, much computer science research has been dedicated to utilizing sensor readings for medical purposes. Throughout this period, the need for virus symptom tracking has become a promising area for remotely deployed sensor networks and platforms. Our research goal is to prove that the temperature readings from these sensor network platforms can be statistically linked to public record, medical case study data. The expected outcome of our project is to prove the correlation between sensor network tracking of remote human temperature data and medical records for COVID cases. The results of this study will prove that tracking human temperature can assist in tracking disease outbreaks in various populations. Our framework platform is comprised of four main modules: (1) Temperature Collection, (2) Internal Data Validation (3) Internal-External data merger, (4) Data Analytics. The temperature data are collected from internal databases, mobile sensing devices and medical health professionals. After collection, the internal data are validated by our software, TAU-FIVE, a multi-tier data quality validation system, then merged with external data sources into a data analytic based data warehouse. The data mart queries are designed to compare the location and date of temperature sensor data with known data sets from government officials. Once blended into a fully operational data warehouse, these data marts produce high quality data analysis linking remotely sensed human temperature readings to sources of disease outbreaks. © 2021 IEEE.