Algorithm for Indoor Positioning Radio Device Based on Channel State Information

The work is devoted to the development of an algorithm for positioning an object of interest in the observed area by analyzing the channel state information of OFDM devices. WiFi routers act as a source of channel state information. The measurement is carried out using a laboratory setup proposed by the team. The positioning algorithm is based on a neural network to solve the classification problem. The work of the algorithm is divided into two stages: online and offline. At the offline stage, information about the observed territory is collected and the neural network is trained. At the Online stage, information from routers is translated into coordinates of an object of interest. Positioning is performed based on the signal phase measured over 56 subcarriers and three pairs of antennas. Experimental studies were carried out that showed the possibility of organizing static positioning of an object of interest with an accuracy of up to 94.58%.