04-04-2023 дата публикации
Номер: CN115913850A
Принадлежит:
The invention discloses an open set modulation identification method based on a residual network, and relates to the technical field of signal identification, and the method comprises the steps: firstly, obtaining baseband signal samples of various modulations, marking the modulation types of the baseband signal samples, and carrying out the grouping of to-be-classified modulation patterns according to the modulation characteristics; preprocessing and recoding the baseband signal sample to form a data set, and dividing the data set into a training set and a test set; secondly, establishing a deep learning model based on a residual network for a modulation identification task; performing supervised training on the deep learning model according to the training set; and finally, inputting the test set into the trained deep learning model, and carrying out modulation signal classification. The method is easy to train, high in convergence speed, multiple in recognition types, high in speed, ...
Подробнее