Multi-modal non-intrusive sleep pattern recognition in elder assistive environment
Résumé
Quality of sleep is an important attribute of an elder's health state and its assessment is still a challenge. Sleep pattern is a significant aspect to evaluate the quality of sleep, and how to recognizethe elder's sleep pattern is an importantissuefor elder-care community. This paper presents a novel multimodal sensing system to monitor the elder's sleep behavior with the pressure sensor matrix and ultra wide band (UWB) tags. Based on the proposed sleep monitoring system, the paper addresses the unobtrusive sleep postures detection and pattern recognition approaches, and the processing methods of experimental data and theclassification algorithms for sleep pattern recognitionare also discussed.