Digital Signal Modulation Recognition Algorithm Based on VGGNet Model
| Autor: | Jiaao Liu, Yang Chen, Dechun Sun, Yu Li, Rui Ma |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Deep learning Feature extraction Pattern recognition 02 engineering and technology 01 natural sciences Convolutional neural network Signal Convolution 010309 optics Support vector machine Signal-to-noise ratio Modulation Computer Science::Computer Vision and Pattern Recognition 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Digital signal Artificial intelligence business |
| Zdroj: | 2019 IEEE 5th International Conference on Computer and Communications (ICCC). |
| DOI: | 10.1109/iccc47050.2019.9064328 |
| Popis: | Aiming at the problem that feature extraction in traditional modulation recognition relies on manual experience and the poor performance of traditional methods in low signal-to-noise ratio (SNR), a deep learning intelligent modulation recognition algorithm based on VGG convolution neural network model is proposed in this paper, which replaces manual design features and improves the recognition performance of digital signals in low SNR. The algorithm first converts the sampled data of communication signals into gray images, then trains the VGGNet model built under PyTorch to extract and select the features of six kinds of digital modulation signals automatically, thus realizing the automatic recognition of digital modulation signals. The simulation results show that the recognition rate can reach over 98% when SNR is -2dB, which is better than the recognition results using support vector machine and other algorithms, thus verifying the validity of this method for digital modulation signal recognition at low SNR. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|