GGIR
Converts raw data from wearables into insightful reports for researchers investigating human daily physical activity and sleep.
Advancing actigraphy-based daily activity and sleep analysis with machine learning
The overarching objective of the project is to enhance sleep research by developing an innovative open analytical tool for quantifying human sleep from high resolution wearable movement sensor data. These data are now widely collected in population studies, which typically involve thousands of participants who are asked to wear the movement sensor on their wrist continuously for a week.
This project is externally funded by the Lilly Research Award Program.
Detecting human sleep from wearable accelerometer data without the aid of sleep diaries
Converts raw data from wearables into insightful reports for researchers investigating human daily physical activity and sleep.
Helps you find a suitable neural network configuration for deep learning on time series.