Repository files navigation

This repository contains the documentation, code and materials for our paper"Discrimination of sleep and wake periods from a hip-worn raw accelerationsensor using recurrent neural networks".The documentation contains code snippets to load the.gt3x and the datafrom the Actiwave.edf files and store the data for the subjects that wornboth devices in a new HDF5 fileBEDTIME_TU7.hdf5 which is compatible withthe pandas API. Later notebooks also show how the manual annotation data can beadded resulting in a newANNOTATED_BEDTIME_TU7.hdf5 file.Further notebooks can be found in which the performed experiments are documentedand in which the data analysis was conducted.

All code here was developed using conda to make it reproducible. To work withthis repository follow the following steps.

1. Clone this repository

git clone https://github.com/Trybnetic/sleep-study.gitcd sleep-study/

2. Install the dependencies

conda create -f environment.yml

3. Activate the environment

conda activate bedtime

4. Work on the notebooks

jupyter notebook

This work was supported by the High North Population Studies at UiT The ArcticUniversity of Norway.