Signal modulation recognition method with signal-to-noise ratio adaptation

By using a signal-to-noise ratio adaptive signal modulation recognition method, the feature weights are adjusted by utilizing the SNR attention module, and feature fusion and convolution processing are performed by combining the MCLDNN model. This solves the problem of low recognition accuracy under low signal-to-noise ratio and achieves higher modulation pattern recognition accuracy and lower overfitting risk.

CN120804803BActive Publication Date: 2026-11-06BEIJING DONGFANG MEASUREMENT & TEST INST
View PDF -1 Cites 0 Cited by

Patent Information

Application Number
CN202510812766.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-18
Publication Date
2026-11-06
Estimated Expiration
2045-06-18

Smart Images

  • Figure CN120804803B_ABST
    Figure CN120804803B_ABST
Patent Text Reader

Abstract

The application discloses a signal modulation recognition method with self-adaptive signal-to-noise ratio. It is related to the field of signal processing, and the steps are as follows: input the IQ information of the signal and the signal-to-noise ratio (SNR) estimation value into a signal modulation recognition model to recognize the modulation mode of the signal; the signal modulation recognition model is an MCLDNN provided with an SNR attention module in a feature fusion module; the SNR attention module can receive the SNR estimation value, obtain the signal-to-noise ratio attention weight according to the SNR estimation value, and receive the signal multi-channel fusion feature map output by the multi-channel fusion convolution layer of the MCLDNN; then the signal-to-noise ratio attention weight is used to weight the signal multi-channel fusion feature map and connect the signal multi-channel fusion feature map with a residual error, so as to output a multi-channel fusion feature combined with the SNR attention; and the multi-channel fusion feature combined with the SNR attention is input into a time sequence module of the MCLDNN.
Need to check novelty before this filing date? Find Prior Art