METHOD FOR PREDICTING STRUCTURE OF INDOOR SPACE USING RADIO SIGNAL PROPAGATION CHANNEL ANALYSIS THROUGH DEEP LEARNING

摘要

Disclosed is a method for predicting a structure of an indoor space using radio signal propagation channel analysis through deep learning. With respect to various indoor spaces, channel data of a radio signal is collected and propagation channel parameter data such as the PDP, AoA, AoD, and the like is extracted. A large amount of propagation channel parameter data is input to an artificial neural network together with vertex coordinate value data of the corresponding indoor space to carry out deep learning for the data in advance. The propagation channel parameter data is extracted from the indoor space to be predicted, the indoor space which is best matched is found based on the learned artificial neural network, and the optimal matching indoor space is predicted by the structure of the indoor space to be predicted.;COPYRIGHT KIPO 2020