| 引用本文: | 张顺生,丁宦城,王文钦.面向辐射源识别的多尺度特征提取与特征选择网络.[J].国防科技大学学报,2024,46(6):141-148.[点击复制] |
| ZHANG Shunsheng,DING Huancheng,WANG Wenqin.Multi-scale feature extraction and feature selection network for radiation source identification[J].Journal of National University of Defense Technology,2024,46(6):141-148[点击复制] |
|
| |
|
|
| 本文已被：浏览 384次 下载 169次 |
| 面向辐射源识别的多尺度特征提取与特征选择网络 |
| 张顺生1,丁宦城1,王文钦2 |
|
(1. 电子科技大学 电子科学技术研究院, 四川 成都 611731;2. 电子科技大学 信息与通信工程院, 四川 成都 611731)
|
| 摘要: |
| 目前应用于辐射源识别的卷积神经网络对时序同相正交(in-phase and quadrature-phase,IQ)信号的处理有两种方式:一种方式是将其变换为图像,另一种方式是提取IQ时序数据的浅层特征。前一种方式会导致算法计算量大,而后一种方式会导致识别准确率低。针对上述问题,提出一种多尺度特征提取与特征选择网络。该网络以IQ信号为输入,经多尺度特征提取网络提取IQ信号的浅层特征和多尺度特征,采用特征选择网络降低多尺度特征的数据维度,通过自适应线性整流单元实现特征增强,使用单个全连接层对辐射源进行分类。在FIT/CorteXlab射频指纹识别数据集上,与ORACLE、CNN-DLRF和IQCNet对比实验表明,所提网络在一定程度上提高了识别准确率,降低了计算量。 |
| 关键词: 辐射源识别 IQ信号 多尺度特征提取 特征选择 |
| DOI：10.11887/j.cn.202406015 |
| 投稿日期：2022-11-28 |
| 基金项目: |
|
| Multi-scale feature extraction and feature selection network for radiation source identification |
| ZHANG Shunsheng1, DING Huancheng1, WANG Wenqin2 |
|
(1. Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China; 2. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China)
|
| Abstract: |
| Convolutional neural networks currently applied to radiation source identification process the time-series IQ( in-phase and quadrature-phase) signals in two ways:one way transforms them into images, and the other way extracts shallow features of the IQ time-series data. The former way leads to a large computational effort of the algorithm, while the latter way leads to a low accuracy of the recognition rate. To address the above problems, a multi-scale feature extraction and feature selection network was proposed. After inputting the IQ signal, the shallow and multi-scale features of the IQ signal were extracted by the multi-scale feature extraction network. Then the data dimension of multi-scale features was reduced by the feature selection network. Feature enhancement was achieved by the adaptive linear rectification unit, and a single fully connected layer was used to classify the radiation source. Comparison experiments with ORACLE, CNN-DLRF and IQCNet on the FIT/CorteXlab radio frequency fingerprint recognition dataset show that the proposed network improves the recognition accuracy and reduces the computational effort to some extent. |
| Keywords: radiation source identification IQ signal multi-scale feature extraction feature selection |
|
|
|
|
|
