18-04-2023 дата публикации
Номер: CN115987722A
Автор:
HE BO,
ZHANG ZHICHEN,
WANG YUKAI,
WANG RONG,
YUAN YAWEI,
LI JUN,
WU BAOHANG,
FU WENWEN,
SUN HAOTIAN,
YANG TIANCI,
WANG JINGHAN
Принадлежит:
The invention relates to the field of high-speed wireless communication, in particular to a deep learning-assisted OFDM (Orthogonal Frequency Division Multiplexing) channel estimation and signal detection method, which comprises the following steps of: firstly, generating a data set through an OFDM system, then constructing a channel estimation model by utilizing a self-normalization network (SNN), and constructing a signal detection model by utilizing a convolutional neural network (CNN) and a bidirectional gating cycle unit (BiGRU); the method comprises the steps that firstly, a data set is input into a neural network, a model is trained, an Adam optimizer and a mean square error loss function are adopted to optimize the network, and finally the network is compared with LS, BiLSTM, GRU and DNN + BiLSTM models. According to the invention, the problems of low channel estimation and signal detection precision, serious network loss and poor bit error rate performance in an OFDM system with ...
Подробнее
