DualSleep dataset for accelerometer-based sleep/wakefulness recognition

The DualSleep dataset contains acceleration and temperature overnight recordings of 29 participants wearing two accelerometers at the thigh and lower back, together with the corresponding sleep stages/annotations (Wake, Non-REM1, Non-REM2, Non-REM3, REM, Movement). The annotation were created using simultaneous Polysomnography recordings. The study protocol was approved by the Regional Committee for Medical and Health research ethics (reference no. 2015/1748/REK midt) and all participants signed a written informed consent before being enrolled in the study. The DualSleep dataset was used for machine learning experiments in our published paper: \"A machine learning model for predicting sleep and wakefulness based on accelerometry, skin temperature and contextual information\" (https://doi.org/10.2147/NSS.S452799)