A fall detection algorithm based on channel state information

Human motion detection based on CSI (Channel State Information) is a hot research topic. Many researchers started to focus on it. In this paper, we employ the CSI to detect fall behavior. Firstly, a data weighting operation to smooth the noise will be implemented. Secondly, we extract behaviors data by effect size. Thirdly, several features will be extracted to represent the original data. Finally, we use neural network to distinguish fall behaviors between several behaviors. Experimental results show a better accuracy of our algorithm.