Recognizing human activity in smart home using deep learning algorithm

There is a topic of interest for many researchers about human activities recognition in recent years. In this paper, we propose the research to recognize human activities by deep learning (DL) algorithm. We collected the data from participants performing activities in order to evaluate the human activities recognition results. After pre-training the deep network, the fine-tuning process begins. Compared with Hidden Markov Model (HMM) and naïve Bayes Classifier (NBC), the experiment results show that the proposed deep learning algorithm is an effective way for recognizing human activities in smart home.