摘要
通信信号自动调制识别在电子战、电子侦察中起着重要的作用。通信信号调制识别的任务是确定信号的调制类型和参数。支持向量机是一种新的通用机器学习方法,这种方法被广泛地应用在模式识别、回归估计和概率密度函数估计中。本文在详细分析了数字调制信号的特点以及小波变换提取瞬态特征原理的基础上,提出了一种利用小波变换支持向量机对数字调制信号进行识别的新方法。该方法通过小波变换将输入向量映射到一个高维特征空间,在这个特征空间内,通过构建最优分类面,即可以用支持向量机对数字调制信号进行分类。计算机仿真结果验证了该方法在不同信噪比条件下具有良好的性能。
Automatic modulation identification plays a significant role in electronic warfare, electronic surveil- lance system and electronic counter measure. The task of modulation recognition of communication signals is to determine the modulation type and signal parameters. Support vector machine （SVM） is a new universal learning machine,which is widely used in the fields of pattern recognition, regression estimation and probability density estimation. In this paper, on the base of analyzing the characteristics of different digitally modulated signals and the principle of extracting the transient signal characteristics using wavelet transform, a new SVM method using wavelet kernel function is proposed, which maps the input vector xi into a high dimensional feature space F. In this feature space F, we can construct optimal hyperplane to realize the maximal margin in this space. That is to say, we can use SVM to classify the digital communication signals given, which show that the proposed method has into different groups. In addition, computer simulation results are good performance under different SNRs.
出处
《电子测量与仪器学报》
CSCD
2009年第3期87-92,共6页
Journal of Electronic Measurement and Instrumentation
关键词
调制识别
小波变换
支持向量机
数字通信信号
modulation recognition
wavelet transform
support vector machine
digital modulated signal
