Risk Management of Smart Homes for Disabled People Based on Neural Networks and IoTs

In this paper, we propose a smart home system for disabled people that recognizes their health status and diagnostic values of some symptoms and then predict if there is an upcoming disease. To build this proposed system, different sensors with raspberry pi are used to collect the symptoms diagnostic values and predict if there is an upcoming disease by implementing a neural network. Two neural network methods are utilized and compared, radial basis function (RBF) neural network and multi-layer perceptron (MLP) neural network. Simulation results show that MLP network is more accurate and efficient for our application.