A method of fall detection based on CSI

Aiming at the problems of high cost, complex deployment and privacy violations of traditional human behavior recognition methods, a method for obtaining channel state information CSI for human behavior recognition and fall detection using commercial Wi-Fi equipment is proposed. The fingerprint database is built by extracting the amplitude and phase characteristics in the channel state information CSI as the base signal and using the power spectrum entropy as a new feature. The support vector machine (SVM) based on artificial fish swarm algorithm (AFSA) is used to classify and identify the action. The optimization of the classification is achieved by optimizing the parameter penalty factor and kernel function parameters in the SVM. According to the verification of real environmental data, the average recognition rate reached 94.64%.