Journal of Systems Engineering and Electronics ›› 2013, Vol. 35 ›› Issue (6): 1307-1311.doi: 10.3969/j.issn.1001-506X.2013.06.30

• 通信与网络 • 上一篇    下一篇

基于SVM算法的短波通信协议识别技术

聂东举1, 叶进2, 闫坤1, 车俐1   

  1. 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
  • 出版日期:2013-06-15 发布日期:2010-01-03

Recognition technology for high frequency communication protocol based on SVM algorithm

Nie Dong-ju1, YE Jin2, YAN Kun1, CHE Li1   

  1. 1. School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China
    2. School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
  • Online:2013-06-15 Published:2010-01-03

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。

Abstract:

Because of time varying dispersion and multi-path propagation, the acquired signal for high frequency (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 defining self entropy. An adaptive recognition algorithm is proposed thereupon. Simulation results, like the parameter optimization results and the recognition accuracies, are demonstrated.It is shown that the proposed method can be adopted in other peer works as well.