作者: Yassine El-Khadiri , Gabriel Corona , Cedric Rose , Francois Charpillet
关键词:
摘要: Early detection of frailty signs is important for the senior population that prefers to keep living in their homes instead moving a nursing home. Sleep quality good predictor monitoring. Thus we are interested tracking sleep parameters like wake patterns predict and detect potential disturbances monitored residents. We use an unsupervised inference method based on actigraphy data generated by ambient motion sensors scattered around senior's apartment. This enables our monitoring solution be flexible robust different types housings it can equip while still attaining accuracy 0.94 period estimates.