Name
Abstract | ||
|---|---|---|
Automatic modulation recognition of signals is one of the primitive tasks in software radio and electronic countermeasures. Nowadays, with the increasingly complex wireless communication channel environment, the accuracy and speed of identification of modulated signals have become increasingly demanding. Thus, this paper proposes a recognition method based on convolutional neural network(CNN) and feature fu-sion to improve the signal recognition accuracy. Using smooth pseudo Wigner-Ville distribution(SPWVD) to convert the one-dimensional signals to images, and the image features extracted by the CNN model are fused with Local binary Patter (LBP) features. CNN running on an embedded platform may not meet the performance requirement, therefore, by optimizing the structure, the network can be embedded on the SOC. The CNN architecture implemented on Xilinx’s ZYNQ platform provides accuracy which is 92.36% and can recognize a image per 0.2344s . Simulation results verify the algorithm’s performance under low signal-to-noise ratio(SNR). |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MWSCAS48704.2020.9184608 | MWSCAS |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Changbo Hou | 1 | 0 | 0.34 |
| Chenyu Fang | 2 | 0 | 0.34 |
| Yun Lin | 3 | 0 | 0.34 |
| Yuqian Li | 4 | 0 | 0.34 |
| Jie Zhang | 5 | 47 | 15.01 |