| 引用本文: | 周东青,王玉冰,王星,等.基于深度限制波尔兹曼机的辐射源信号识别.[J].国防科技大学学报,2016,38(6):136-141.[点击复制] |
| ZHOU Dongqing,WANG Yubing,WANG Xing,et al.Radar emitter signal recognition based on deep restricted Boltzmann machine[J].Journal of National University of Defense Technology,2016,38(6):136-141[点击复制] |
|
| |
|
|
| 本文已被：浏览 7769次 下载 6715次 |
| 基于深度限制波尔兹曼机的辐射源信号识别 |
| 周东青1, 王玉冰1, 王星1, 程相东2, 肖吉阳3 |
|
(1.空军工程大学 航空航天工程学院， 陕西 西安 710038;2.空军西安飞行学院， 陕西 西安 710306;3.空军工程大学 装备管理与安全工程学院， 陕西 西安 710051)
|
| 摘要: |
| 针对电子侦察中使用常规参数难以有效识别复杂体制雷达信号的问题，提出利用深度限制波尔兹曼机对辐射源识别的模型。模型由多个限制波尔兹曼机组成，通过逐层自底向上无监督学习获得初始参数，并用后向传播算法对整个模型进行有监督的参数微调，利用Softmax进行分类识别。通过仿真实验表明该模型能对辐射源进行有效的特征提取和分类识别，具有较高的识别精度和较强的鲁棒性。 |
| 关键词: 辐射源信号识别 深度学习 限制波尔兹曼机 |
| DOI：10.11887/j.cn.201606022 |
| 投稿日期：2015-06-19 |
| 基金项目:国家自然科学基金资助项目（61372167） |
|
| Radar emitter signal recognition based on deep restricted Boltzmann machine |
| ZHOU Dongqing1, WANG Yubing1, WANG Xing1, CHENG Xiangdong2, XIAO Jiyang3 |
|
(1.Aeronautics and Astronautics Engineering College, Air Force Engineering University, Xi′an 710038, China;2.PLA Air Force Xi′an Flight Academy, Xi′an 710306, China;3. Equipment Management and Safety Engineering College, Air Force Engineering University, Xi′an 710051, China)
|
| Abstract: |
| To deal with the problem of radar emitter recognition caused by parameter complexity and agility of muti-function radars in electronic intelligence reconnaissance field, a new recognition model based on deep restricted Boltzmann machine was proposed. The model was composed of multiple restricted Boltzmann machine. A bottom-up hierarchical unsupervised learning was used to obtain the initial parameters, and then the traditional back propagation algorithm was conducted to fine-tune the network parameters, and the Softmax was used to classify the results at last. Simulation and comparison experiment shows that the proposed method has the ability of extracting the parameter features and recognizing the radar emitters, and it has strong robustness as well as high recognition rate. |
| Keywords: radar emitter signal recognition deep learning restricted Boltzmann machine |
|
|
