A Deep Reinforcement Learning based Human behavior Prediction Approach in Smart Home Environments

Human behaviors(activities) recognition is a hot research topic for many researchers in recent years. In this paper, we propose an approach to recognize human activities by deep reinforcement learning (DL) algorithm. We use a collection of some publicly available real-life datasets from the smart home environment domain. Based on selected predictive model architecture and Deep Q-network (DQN), the human behaviors recognition results are envaluated, the experiment result shows that the proposed deep learning algorithm is an effective way for recognizing human activities in smart home.