| 引用本文: | 王垚,满欣,尤红雨,等.矩阵变换特征与码序列联合学习的卷积码识别方法.[J].国防科技大学学报,2023,45(5):38-47.[点击复制] |
| WANG Yao,MAN Xin,YOU Hongyu,et al.Convolutional codes recognition method based on joint learning of matrix transformation features and code sequences[J].Journal of National University of Defense Technology,2023,45(5):38-47[点击复制] |
|
| |
|
|
| 本文已被：浏览 5271次 下载 3031次 |
| 矩阵变换特征与码序列联合学习的卷积码识别方法 |
| 王垚1,满欣2,尤红雨1,明亮3,刘伟松1,黄知涛1,4 |
|
(1. 国防科技大学 电子科学学院, 湖南 长沙 410073;2. 海军工程大学 电子工程学院, 湖北 武汉 430033;3. 中国人民解放军92001部队, 山东 青岛 266005;4. 国防科技大学 电子对抗学院, 安徽 合肥 230037)
|
| 摘要: |
| 现有基于深度学习的卷积码识别方法仍存在参数规模较大、识别性能较弱等不足。针对该问题,提出了一种基于矩阵变换特征与码序列联合学习的卷积码识别方法。将接收到的码字序列排列成矩阵形式,利用软信息剔除可靠性较低的码字,通过一种新的矩阵变换算法得到特征矩阵。在识别时,将原始码字矩阵和特征矩阵输入到具有多模态数据联合学习能力的网络模型,在神经网络中完成特征的提取融合与卷积码的识别。仿真结果表明,所提方法性能明显优于现有基于深度学习的识别方法,特别是对于高码率卷积码；当码率较低时,同样优于传统识别方法。当信噪比达到5 dB时,25种不同参数卷积码的识别率均可达到100%。 |
| 关键词: 信道编码 卷积码识别 矩阵变换 联合学习 |
| DOI：10.11887/j.cn.202305005 |
| 投稿日期：2022-10-24 |
| 基金项目:国防科技大学青年创新资助项目(18/19-QNCXJ) |
|
| Convolutional codes recognition method based on joint learning of matrix transformation features and code sequences |
| WANG Yao1, MAN Xin2, YOU Hongyu1, MING Liang3, LIU Weisong1, HUANG Zhitao1,4 |
|
(1. College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China;2. College of Electronic Engineering, Naval University of Engineering, Wuhan 430033, China;3. The PLA Unit 92001，Qingdao 266005, China;4. College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China)
|
| Abstract: |
| Existing deep learning based convolutional code recognition methods still have shortcomings such as large parameter sizes and weak recognition performance. Aiming at this problem, a convolutional code recognition method based on joint learning of matrix transform features and code sequences was proposed. The received codeword sequence was arranged into a matrix form, and the soft information was used to eliminate the codewords with low reliability. Then, a new matrix transformation algorithm was used to obtain the feature matrix. During the recognition process, the original matrix of code words and the matrix of features were fed into a network model with a joint learning capability for multimodal data. The feature extraction fusion and convolution code recognition were completed in the neural network. Simulation results show that the recognition performance of the proposed method is significantly better than the existing recognition methods based on deep learning, especially for high bit rate convolutional codes. When the rate is low, the proposed method is also better than traditional methods. When the signal-to-noise ratio reaches 5 dB, the recognition rate of 25 convolutional codes with different parameters can reach 100%. |
| Keywords: channel codes convolutional codes recognition matrix transformation joint learning |
|
|
|
|
|
