基于信号特征空间的TDCS干扰分类识别

发布时间：2018-01-20 16:50

本文关键词： 变换域通信系统干扰分类识别信号特征空间支持向量机　出处：《系统工程与电子技术》2017年09期 　论文类型：期刊论文

【摘要】：针对变换域通信系统中干扰信号的分类识别问题,提出了一种基于信号特征空间的支持向量机(signal feature space-support vector machine,SF-SVM)干扰分类算法。首先,基于干扰信号模型和信号空间理论对干扰信号进行特征提取,并建立信号特征空间,进而针对二分类和多分类问题提出了SF-SVM分类算法,设计了干扰信号的多分类识别器。仿真结果表明,与干扰信号的传统分类算法相比,SF-SVM不仅提高了分类精度,而且缩短了训练时间;设计的多分类识别器在信噪比达到8dB时,对6种干扰信号识别性能及对变换域通信系统性能都有所提升。
[Abstract]:This paper aims at the classification and identification of interference signals in transform domain communication systems. A signal feature space-support vector machine based on signal feature space is proposed. The interference classification algorithm of SF-SVM. Firstly, based on the interference signal model and signal space theory, the feature extraction of interference signal is carried out, and the signal feature space is established. Then, the SF-SVM classification algorithm is proposed for two-classification and multi-classification problems, and a multi-classification recognizer for jamming signal is designed. The simulation results show that the algorithm is compared with the traditional classification algorithm of interference signal. SF-SVM not only improves the classification accuracy, but also shortens the training time. When the signal-to-noise ratio (SNR) of the multi-class recognizer is up to 8dB, the performance of the proposed multi-class recognizer can improve the performance of 6 kinds of interference signals and the communication system in transform domain.
【作者单位】：空军工程大学信息与导航学院;中国电子科技集团公司航天信息应用技术重点实验室;
【基金】：国家自然科学基金(61401499) 新技术研究高校合作项目(KX162600022)资助课题
【分类号】：TN911.4;TN914
【正文快照】： 0引言变换域通信系统(transform domain communicationsystem,TDCS)利用在优选的变换域内构造与干扰信号正交的基函数实现干扰抑制,其优良的抗干扰、抗截获性能得到广泛关注[1],干扰的分类识别是制约TDCS抗干扰能力的重要因素。由于单一变换域技术只能针对性应对一种干扰,干扰

【相似文献】