基于多节点信息融合和协作的信号调制方式识别  

Modulation recognition based on cooperative and information fusion of multi-nodes

作　　者：杨单[1,2] 李超锋[1] 杨健[1] 

机构地区：[1]中南民族大学管理学院,武汉430074 [2]华中科技大学计算机学院,武汉430074

出　　处：《计算机工程与应用》2014年第16期7-11,共5页Computer Engineering and Applications

基　　金：湖北省教育厅科学技术项目(No.QZY11009);中南民族大学校基金资助项目(No.YZQ10001)

摘　　要：针对单节点在低信噪比环境下调制识别率低的难题,提出了基于一种多节点信息融合和协作的信号调制方式识别方法。首先设计多个传感器节点协作方案,并提取每节点特征,然后中心节点将各节点特征进行融合,最后采用最小二乘支持向量机建立信号调制分类器。仿真结果表明,相比于其他信号调制识别方法,该方法提高了信号调制识别精度,对信噪比环境具有更好的自适应性。Aiming at the low recognition rate when SNR is low in single node, a modulation recognition method based on cooperative and information fusion of multi-nodes is proposed in this paper. The cooperative method is designed for wire-less sensor networks nodes, and features of each node are extracted, and then feature vector is combined and fused by cen-tral node. The classifier of recognizing the signals is established by least squares support vector machine. The simulation results show that the proposed method has improved the recognition rate compared with other methods and has better adaptability to SNR environments.

关 键 词：调制识别 分布式协作 最小二乘支持向量机 无线传感器网络 

分 类 号：TN929.5[电子电信—通信与信息系统]