Recurrent Neural Network for Human Activity Recognition in Smart Home

One of the most important functions of smart home is to monitor and assist individuals who are old or disabled. Recognizing the human activities is critical for the smart home application. In this paper, recurrent neural network (RNN) is applied to recognize the human activities. To evaluate the accuracy of the recognition algorithms, the results using real data collected from participants performing activities were assessed. With proper feature selections, the results of recurrent neural network show the significant ability to recognize human activities in smart home.