Skip to content

An ensemble learning model and cross-validation method for time series data. We predict alertness in NASA astronauts given time-varying environmental stressors and behavioral measurements.

Notifications You must be signed in to change notification settings

danni-tu/TRISH_dynamic_prediction

Repository files navigation

Dynamic Ensemble Prediction of cognitive performance in spaceflight

This paper is now published in Nature Scientific Reports (open access link).

We identify predictors of neurobehavioral alertness over the course of a 6-month spaceflight mission, using self-reported, cognitive, and environmental data collected from 24 astronauts on the International Space Station.

Using time-varying and discordantly-measured environmental, operational, and psychological covariates, we propose an ensemble prediction model to accurately and dynamically predict neurobehavioral alertness at the individual level. Our method is broadly applicable to environmental studies where the main goal is accurate, individualized prediction of human behavior involving a mixture of person-level traits and irregularly measured time series.

alt text

Code documentation for “Dynamic Ensemble Prediction of Cognitive Performance in Space” can be found at https://danni-tu.github.io/TRISH_dynamic_prediction/.

About

An ensemble learning model and cross-validation method for time series data. We predict alertness in NASA astronauts given time-varying environmental stressors and behavioral measurements.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published