Forecasting the Wellness of Elderly through SNMS

Accurate and timely information collection is important for physicians to provide prompt and appropriate treatment for patients. In this paper, a smart nursing home monitoring system which can predict the health conditions of the elderly people who live in the nursing home is presented. A framework integrating temporal and spatial contextual information for evaluating the wellness of an elderly has been modeled. A novel activity detection process based on the location information collects by the RFID technology in performing essential daily activities has been designed and developed. A BP neural network is trained using the activity information of the elderly live in the nursing home, wellness models are tested and the results are encouraging.