Patient monitoring process with touch (wearable) and touchless RFID sensors

Human activity recognition from sensor readings has proved to be an effective approach in pervasive computing for smart healthcare. Recent approaches to ambient and assisted living (AAL) within a home or community setting offers people the prospect of more individually-focused care and improved quality of living. However, most of the available AAL systems are often limited by computational cost. In this research unwearable human activity classification framework using the multivariate Gaussian can be adopted and proposed. The classification framework augments the prior information from the passive RFID tags to obtain a more detailed activity profiling. The maximum likelihood estimation (MLE) algorithm could be applied to learn the parameters in the human activity model. Modelling and experimental evaluations will be conducted in a mock apartment environment. Then the sampled activities predicted using a new dataset of the same activities and high prediction accuracy may be established. The study is looking to the prediction accuracy of the algorithm applied and compared to the number of the samples collected.