基于决策理论的数字调制信号识别

Automatic modulation recognition of digital communication signals based on a decision-theoretic approach

由于多调制的存在,对于一个通信信号进行接收解调的前提条件是首先要确定该信号的调制样式,因此信号调制样式的自动识别是软件无线电接收机中必须具备的功能之一。文中研究了6种常用数字调制信号识别的特征参数集,并采用决策树判别方法进行分类识别。仿真结果表明,在SNR≥5 dB时,识别正确率在99%以上,且当SNR≥20 dB时,识别正确率达到100%。其特点是,算法简单,识别正确率高,达到了自动分类识别的目的,并有利于实现识别的实时化。

For the using of multi-modulation, the precondition of receiving and demodulating signal is to decide the type of the modulation. So automatic recognition of modulation signal is a required function of software radio receiver. In this paper, six types of digital modulations are recognized by using four effective key features and utilising the decision-theoretic approach. The simulation results shows that overall success rate is over 99% at SNR≥5dB and 100% at SNR ≥20 dB. This algorithm is verified by its good performance. It has simple structure, less calculation and good performance of real time. It can realize automatic modulation recognition.