If you use this dataset please cite: R. J. Ward et al., "FluNet: An AI-Enabled Influenza-like Warning System," in IEEE Sensors Journal, doi: 10.1109/JSEN.2021.3113467. This repository contains two datasets. The thermal face dataset contains images of twenty participants in the thermal domain with and without a face mask and at several approximate facial rotations (-90, -45, 0, +45, +90) degrees as well as looking downwards towards a mobile phone. This dataset has 261 images in total. The cough dataset consists of 53,471 seconds of background noise samples. 1,557 seconds of cough sounds and 40,856 of augmented coughs with random background sounds at a random volume ratio. Among other things, these datasets can be used to train machine learning models to help predict potentially symptomatic COVID-19 cases.