基于SVM算法的短波通信协议识别技术  

Recognition technology for high frequency communication protocol based on SVM algorithm

作　　者：聂东举[1] 叶进[2] 闫坤 车俐[1] 

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004 [2]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《系统工程与电子技术》2013年第6期1307-1311,共5页Systems Engineering and Electronics

基　　金：国家自然科学基金(61163060;61261034);广西区基金重点项目(2011GXSFD1802)资助课题

摘　　要：受时变色散信道及多径效应的影响,短波通信协议的识别存在截获信号质量差、单一特征识别准确率低等问题。提出了协议特征向量和自熵,设计了一种具有自适应学习能力的协议识别模型和相应的识别算法,最后给出了参数寻优结果以及识别准确率分析。本文的工作为短波通信协议识别技术的应用提供了重要参考。Because of time-varying dispersion and multi-path propagation, the acquired signal for high fre- quency （HF） communication is inferior. Thus the protocol features for HF communication standards are hard to obtain. A novel protocol model for HF communication is proposed by employing protocol feature vector and defi- ning self-entropy. An adaptive recognition algorithm is proposed thereupon. Simulation results, like the param- eter optimization results and the recognition accuracies, are demonstrated. It is shown that the proposed method can be adopted in other peer works as well.

关 键 词：短波通信 协议识别 支持向量机 

分 类 号：TN915.04[电子电信—通信与信息系统]