| 从GAR模型参数提取特征的数字调制识别新方法 |
| |
| 引用本文： | 陆明泉, 肖先赐, 李乐民. 从GAR模型参数提取特征的数字调制识别新方法[J]. 电子与信息学报, 1999, 21(2): 145-151. |
| |
| 作者姓名： | 陆明泉 肖先赐 李乐民 |
| |
| 作者单位： | 电子科技大学电子工程学院，电子科技大学电子工程学院，电子科技大学电子工程学院 成都 610054，成都 610054，成都 610054 |
| |
| 摘 要： | 本文提出了一种从观察序列的广义自回归(GAR)模型参数提取待识别信号的伪瞬时中心频率和伪瞬时3dB带宽特征,并利用神经网络分类器的数字调制识别新方法。这种方法充分利用了GAR模型良好的抗噪声能力和神经网络优异的模式分类能力,能有效地改善低SNR条件下的调制识别性能。计算机模拟结果证实了该方法具有很高的识别率和良好的稳健性。
|
| 关 键 词： | 调制识别 广义自回归模型 特征提取 神经网络分类器 |
| 收稿时间： | 1997-09-11 |
| 修稿时间： | 1998-06-08 |
A NEW DIGITAL MODULATION RECOGNITION METHOD USING FEATURES EXTRACTED FROM GAR MODEL PARAMETERS |
| |
| Lu Mingquan, Xiao Xianci, Li Lemin. A NEW DIGITAL MODULATION RECOGNITION METHOD USING FEATURES EXTRACTED FROM GAR MODEL PARAMETERS[J]. Journal of Electronics & Information Technology, 1999, 21(2): 145-151. |
| |
| Authors: | Lu Mingquan Xiao Xianci Li Lemin |
| |
| Affiliation: | School of Electronic Engineering University of Electronic Science and Technology of China Chengdu 610054 |
| |
| Abstract: | A new digital modulation recognition method is proposed, which is based on the features extracted from generalized autoregressive (GAR) model parameters of the obsevered sequence and the use of neural network classifier. Because of the better noise suppression capacity of the GAR model and the powerful pattern classification capacity of the neural network classifier, the new method can significantly improve the recognition performance in lower SNR. Computer simulations also show that the new method possesses higher recognition ratio and better robustness. |
| |
| Keywords: | Modulation recognition GAR model Feature extraction Neural network classifier |
| 本文献已被 CNKI 等数据库收录！ |
| 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 |
