基于模糊函数SVD和改进S3VM的雷达信号识别

发布时间：2018-06-30 10:07

本文选题：雷达信号识别 + 半监督支持向量机　；参考：《计算机工程与应用》2017年06期

【摘要】：为提升在日趋复杂的电子对抗环境中对雷达信号识别的准确率,提出了一种基于启发式采样搜索(Heuristic Sampling Search,HSS)改进S3VM的雷达辐射源信号识别算法。根据模糊函数理论,通过对雷达信号的模糊函数进行奇异值分解(SVD),提取出奇异向量作为雷达信号识别的特征参数;针对传统的半监督支持向量机(Semi-supervised SVM,S3VM)的不足,利用改进的S3VM构建分类器对雷达信号进行分类,完成对测试样本的识别。该方法通过启发式采样搜索来寻求具有代表性的多个大边缘低密度的分类决策面,有效解决传统S3VM分类精度低且分类性能不稳定等缺点。实验结果表明,在雷达信号识别中,该算法明显提高了分类准确率。
[Abstract]:In order to improve the accuracy of radar signal recognition in the increasingly complex electronic countermeasure environment, an improved radar emitter signal recognition algorithm based on heuristic sampling search (HSS) is proposed. According to the theory of fuzzy function, singular vector is extracted as the characteristic parameter of radar signal recognition by using singular value decomposition (SVD) of fuzzy function of radar signal. The improved S3VM classifier is used to classify radar signals, and the test samples are identified. This method uses heuristic sampling search to find representative decision surfaces with large edges and low density, which can effectively solve the shortcomings of traditional S3VM classification, such as low accuracy and unstable classification performance. The experimental results show that the algorithm improves the classification accuracy obviously in radar signal recognition.
【作者单位】：空军工程大学航空航天工程学院;
【基金】：航空科学基金(No.20152096019)
【分类号】：TN957.51

【相似文献】