基于ICA和SVM的混合通信信号调制方式识别  

Mixed communication signals modulation mode identification based on ICA and SVM

作　　者：王立东[1] 张晓林 孔挺[2] 

机构地区：[1]哈尔滨工程大学信息与通信学院,哈尔滨150001 [2]海军飞行学院教研部,葫芦岛125001

出　　处：《仪器仪表用户》2011年第2期62-65,共4页Instrumentation

摘　　要：本文提出了一种基于独立分量分析(ICA)和支持向量机(SVM)的混合通信信号调制方式识别的方法,针对接收的信号多为混叠信号、先验知识少、分离困难等特点,采用独立分量分析的方法,将这些独立的信号分离开来。然后引入基于SVM的信号调制方式识别方法,从通信信号的瞬时幅度、相位、频率等特性中提取了6个特征参数,并用SVM调制识别器进行识别。仿真结果证明,在信噪比不低于10dB时,算法的识别率可以达到95%以上,证明了此方法的可行性。This paper presents a method of mixed communication signals modulation mode identification, the method is based on independent component analysis （ICA） and support vector machine （SVM） , according to the receive signal for aliasing signal, prior knowledge less、 seParation difficult and so on, making use of independent analysis method, it separates the independent signal. Then the paper introduces the signal modulation mode identification method that is based on SVM and the method extracts six characteristic parameters from the communication signal＇ s the instantaneous amplitude, phase and frequency characteristics, then it uses SVM modulation identifier to recognize them. The simulation results show that when the signal-to-noise ratio is not below 10dB, the recognition rate of the algorithm can achieve the above 95% and prove the feasibility of this method.

关 键 词：混合通信信号 独立分量分析 支持向量机 调制方式识别 

分 类 号：TN911.72[电子电信—通信与信息系统]