Modulation mode identification method based on deep learning

Abstract

The invention provides a modulation mode identification method based on deep learning, which is used for solving the problem of low identification accuracy in the prior art, and comprises the following implementation steps of: (1) obtaining a training set and a test set; (2) establishing a neural network NNs; (3) dividing the training set into a plurality of sub-training sets based on the signal-to-noise ratio, and respectively training the neural network NNs by using the sub-training sets to obtain a plurality of trained neural networks; and (4) evaluating the signal-to-noise ratio snr of theto-be-tested modulation signal, selecting an applicable trained neural network according to the interval where the snr is located, and identifying the modulation mode of the to-be-tested modulation signal. When the neural network NNs are trained, the internal relation and rule of the sample data and the sample labels of all the sub-training sets can be accurately found, the learning effect of theneural network NNs is enhanced, the recognition accuracy is improved, and meanwhile self-adaptive modulation mode recognition based on the signal-to-noise ratio is achieved. The method can be used inthe fields of modulation mode identification and the like in non-cooperative communication.

Description

technical field [0001] The invention belongs to the field of communication technology, and relates to a modulation mode identification method based on deep learning, in particular to a modulation mode identification method based on signal-to-noise ratio segmented training neural network, which can be used in the identification of modulation modes in non-cooperative communication and other fields . Background technique [0002] In the wireless transmission system, the transmitter moves the spectrum of the baseband signal to a higher carrier frequency through modulation, so that the spectrum of the modulated signal matches the band-pass characteristics of the channel to improve transmission performance. The modulation methods of the signal are various. For example, analog modulation methods include amplitude modulation (AM), double sideband (DSB), and single sideband (SSB), and digital modulation methods include amplitude shift keying (Amplitude Shift Keying, ASK), frequency s...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies in the above-mentioned prior art, and provide a modulation method recognition method based on deep learning, which is used to solve the technical problem of low recognition accuracy existing in the prior art

Images