Synthetic Event Time Series Health Data Generation

no code implementations • 14 Nov 2019 • Saloni Dash, Ritik Dutta, Isabelle Guyon, Adrien Pavao, Andrew Yale, Kristin P. Bennett

Due to the complexity of the real data, in which each patient visit is an event, we transform the data by using summary statistics to characterize the events for a fixed set of time intervals, to facilitate analysis and interpretability.

Generative Adversarial Network Time Series +1