AN OFDM CHANNEL ESTIMATION AND SIGNAL DETECTION METHOD BASED ON DEEP LEARNING

AN OFDM CHANNEL ESTIMATION AND SIGNAL DETECTION METHOD BASED ON DEEP LEARNING The present disclosure relates to an OFDM channel estimation and signal detection method based on deep learning. In an aspect, the OFDM channel estimation and signal detection method (100) based on deep learning comprises steps of constructing (102) a neural network comprising a channel estimation unit and a signal detection unit, optimizing (110) the initial prediction original signals corresponding to each subcarrier by using the signal detection unit (102) to obtain input data of the signal detection unit, training (112) the neural network by using a data sample of a multipath channel model matrix, applying (114) the trained neural network to the complex environment unmanned aerial vehicle OFDM data chain system in an off-line manner, estimating a channel and detecting a signal. (Fig. 1 will be the reference figure) - 12- rage i 01 1 Constructing a neural network. Calculating an initial channel impulse response coefficient. Splitting and combining the real part and the imaginary part of the initial channel impulse response coefficient. 106 Iterating channel parameters. Optimizing the initial prediction original signals corresponding to each subcarrier. 110 Training the neural network by using a data sample of a multipath channel model matrix. 112 Applying the trained neural network to the complex environment unmanned aerial vehicle OFDM data chain system in an off-line manner. 114 Fig. 1 Flowchart of an OFDM channel estimation and signal detection method based on deep learning.