Determining the Exact Indoor Location of a Person Using the Channel State Information from the Wi-Fi Router

The work is devoted to the development of a method for determining the exact location of a person indoor using channel state information received from a Wi-Fi router. The method proposed in this paper is based on processing the phase and amplitude values obtained from the router's service packets by a fully connected neural network. To conduct the experiments, measurements were made with the participation of four people of different genders and physiques, as a result of which more than 500 thousand values of phases and amplitudes were obtained. During the experiments, an accuracy of over 90% was obtained.