In order to advance, we beleiveve that public health practitioners seeking to use novel datasets and techniques and researchers from data mining and machine learning developing novel tools for solving problems in the public health policy planning process need to collaborate more.
This project serves to introduce an efficient non-parametric probabilistic deep neural model, EpiFNP, to directly model forecasts as stochastic process and introduce Neural Gaussian Process based deep learning models as well.
In this project, we formulate a spectral characterization of such models by establishing its epidemic threshold, and demonstrate its utility in clinical applications with experiments on real hospital data.
more
URBAN-NET analyzes “what-if” scenarios and their propagation of effects within and across CISs using consequence cascade models based on the topology of the network. This is a robust operational system integrated with ORNL EAGLE-I tool by enabling real-time CIS interdependency analysis.
more
In this paper, we demonstrate that university policymakers can mitigate these tradeoffs by leveraging anonymized data from their WiFi infrastructure to learn community mobility (WiMob) and in turn explore more granular policies like localized closures (LC).
more
