| 基于单通道多尺度图神经网络的自动调制识别 |
| |
| 引用本文： | 国强, 聂孟允, 戚连刚, Kaliuzhnyi Mykola. 基于单通道多尺度图神经网络的自动调制识别[J]. 电子与信息学报, 2023, 45(5): 1575-1584. doi: 10.11999/JEIT220840 |
| |
| 作者姓名： | 国强 聂孟允 戚连刚 Kaliuzhnyi Mykola |
| |
| 作者单位： | 1.哈尔滨工程大学信息与通信工程学院 哈尔滨 150001;;2.先进船舶通信与信息技术工业和信息化部重点实验室 哈尔滨 150001;;3.哈尔科夫国立无线电电子大学 哈尔科夫 61166 |
| |
| 基金项目： | 国家重点研发计划(2018YFE0206500)，国家自然科学基金(62071140)，中央高校基本科研业务费专项资金(3072022QBZ0801) |
| |
| 摘 要： | 针对自适应可见性图(AVG)算法复杂度过高且精度提升不明显的缺点，该文提出一种基于单通道多尺度图神经网络(SMGNN)的自动调制识别(AMR)框架，并对框架各个部分进行了可解释性研究。首先利用多层感知机和1维卷积自适应地实现了单通道信号序列和图之间的映射，有效降低了AVG算法的复杂度；其次，设计了一种多尺度图神经网络，将不同分辨率的特征进行融合，提升了模型识别准确率。实验表明，该文提出的SMGNN算法相比于AVG算法节省了近1/2的参数量，且识别精度得到了较大的提升。
|
| 关 键 词： | 自动调制识别 图神经网络 自适应可见性图 特征融合 |
| 收稿时间： | 2022-06-24 |
| 修稿时间： | 2022-11-08 |
Automatic Modulation Recognition Based on Single-channel Multi-scale Graph Neural Network |
| |
| GUO Qiang, NIE Mengyun, QI Liangang, Kaliuzhnyi Mykola. Automatic Modulation Recognition Based on Single-channel Multi-scale Graph Neural Network[J]. Journal of Electronics & Information Technology, 2023, 45(5): 1575-1584. doi: 10.11999/JEIT220840 |
| |
| Authors: | GUO Qiang NIE Mengyun QI Liangang Kaliuzhnyi Mykola |
| |
| Affiliation: | 1. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China;;2. Key Laboratory of Advanced Marine Communication and Information Technology Ministry of Industry and Information Technology, Harbin 150001, China;;3. Kharkiv National University of Radio Electronics, Kharkiv 61166, Ukraine |
| |
| Abstract: | Considering the shortcomings of the Adaptive Visibility Graph (AVG) algorithm being too complex and the accuracy improvement is not significant, an Automatic Modulation Recognition(AMR) framework based on Single-channel Multi-scale Graph Neural Network (SMGNN) is proposed and interpretability studies are conducted on the various parts of the framework. Firstly, the multi-layer perceptron and one-dimensional convolutional adaptive are used to realize the mapping between single-channel signal sequences and graphs, which reduces effectively the complexity of AVG algorithms. Secondly, a multi-scale graph neural network is designed to fuse the features of different resolutions, which improves the accuracy of model recognition. Experiments show that the SMGNN algorithm proposed in this paper saves nearly half of the parameter amount compared with the AVG algorithm, and the recognition accuracy has been greatly improved. |
| |
| Keywords: | Automatic Modulation Recognition(AMR) Graph Neural Network(GNN) Adaptive Visibility Graph(AVG) Feature Fusion(FF) |
|
| 点击此处可从《电子与信息学报》浏览原始摘要信息 |
|
点击此处可从《电子与信息学报》下载全文 |
