首页 | 本学科首页   官方微博 | 高级检索  
     

一种混合模式的神经网络自动调制识别器
引用本文:赖惠成, 褚辉. 一种混合模式的神经网络自动调制识别器[J]. 电子与信息学报, 2008, 30(5): 1203-1205. doi: 10.3724/SP.J.1146.2007.00515
作者姓名:赖惠成  褚辉
作者单位:新疆大学信息科学与工程学院,乌鲁木齐,830046;新疆大学信息科学与工程学院,乌鲁木齐,830046
基金项目:教育部跨世纪优秀人才培养计划
摘    要:数字信号自动调制识别(AMR)有基于决策论和统计模式两种方法,该文提出一种将两者相结合的自动调制识别系统,利用提取决策论特征向量集和统计特征向量集相结合的特征参数,使用带动量项的自适应权重的BP神经网络对MASK,MFSK,MPSK,MQAM等4类信号进行分类识别。当信噪比在0-10dB,在估计载频与实际载频相差0-100Hz的情况下正确识别率仍高达97%以上,实验证明这种分类识别方法的鲁棒性和实用性。

关 键 词:数字调制   特征提取   自动调制识别   神经网络
文章编号:1009-5896(2008)05-1203-03
收稿时间:2007-04-06
修稿时间:2007-04-06

An Automatic Modulation Recognizer Using Neural Networks Based on the Hybrid Mode
Lai Hui-cheng, Chu Hui . An Automatic Modulation Recognizer Using Neural Networks Based on the Hybrid Mode[J]. Journal of Electronics & Information Technology, 2008, 30(5): 1203-1205. doi: 10.3724/SP.J.1146.2007.00515
Authors:Lai Hui-cheng  Chu Hui
Affiliation:College of Information Science & Engineering, Xinjiang University, Urumqi 830046, China
Abstract:On automatic modulation there are two approaches, decision-theoretic and statistical pattem. An automatic modulation recognition system to recognize four digital signal classes as MASK, MFSK, MPSK, MQAM is proposed in this paper, which using decision-theoretic based feature set addition to statistical pattem based feature set with momentum auto-adapted weight BP neural network. Performance is generally good when Signal to Noise Ratios (SNR) in 0-10dB, and the estimated carrier frequency differs from the actual carrier frequency of 0-100Hz, simulations show the results even larger than 97%, that confirm the robustness and practicability of this recognition method.
Keywords:Digital modulation  Feature extraction  Automatic Modulation Recognition(AMR)  Neural network  
本文献已被 CNKI 维普 万方数据 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
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号