核Fisher判别分析在数字信号分类中的应用

doi:10.13190/jbupt.201101.35.zhoux

北京邮电大学学报 ›› 2011, Vol. 34 ›› Issue (1): 35-39.doi: 10.13190/jbupt.201101.35.zhoux

核Fisher判别分析在数字信号分类中的应用

周欣,吴瑛

信息工程大学信息工程学院，郑州 450002

收稿日期:2010-03-03 修回日期:2010-07-02 出版日期:2011-02-28 发布日期:2011-02-28
通讯作者: 周欣 E-mail:zx007_0_0@126.com
基金资助:
国家自然科学基金项目(60872043)

Application of Kernel Fisher Discriminant Analysis to  Digital Signal Classification

Received:2010-03-03 Revised:2010-07-02 Online:2011-02-28 Published:2011-02-28

摘要/Abstract

摘要：

为了提高通信信号的识别精度，提出了一种基于核Fisher判别分析（KFDA)的数字调制信号分类器设计方法. 将接收信号的高阶累积量作为分类特征向量，利用核函数的思想把非线性向量映射到一个高维空间，并在高维空间中利用线性Fisher判别分析实现数字信号的分类. 将多类分类器分解成一系列二类问题，并给出了KFDA用于信号分类的详细流程. 仿真实验结果表明，当选择合适的核参数时，基于KFDA的分类精度与支持向量机相当，但由于避免了求解非线性优化问题，故计算复杂度低，训练时间短.

关键词: 高阶累积量, 核Fisher判别分析, 核函数, 信号分类

Abstract:

In order to improve signal classification accuracy, a new classification method based on kernel Fisher discriminant analysis (KFDA) is given in the digital modulation signal classification. The higher order cumulants of the received signals are used as the classification vectors firstly, then the kernel thought is used to map the feature vector to the high dimensional feature space nonlinearly and linear Fisher discriminant analysis is applied to signal classification. The multiclass classifier is decomposed to multiple twokinds classifiers, and the classification steps of signal recognition based on kernel Fisher discriminant analysis are described in detail. It is concluded based on experiment that when proper parameters are selected, it will almost get the same classification accuracy as the support vector machine classifier. Meanwhile, support vector machine requires less time and computational complexity is lower because KFDA avoids solving the nonlinear optimization problem.

Key words: highorder cumulant, kernel Fisher discriminant analysis, kernel function, signal classification

周欣,吴瑛. 核Fisher判别分析在数字信号分类中的应用[J]. 北京邮电大学学报, 2011, 34(1): 35-39.

参考文献

[1] Nandi A K, Azzouz E E. Automatic modulation recognition [J]. Signal Processing, 1995, 46(2): 211-222. [2] Dobre O A, Abdi A, Bar-Ness Y, et al. Survey of automatic modulation classification techniques: classical approaches and new trends[J]. IET Commun, 2007, 1(2): 137-156. [3] Cheng Hanwen, Han Hua, Wu Lenan, et al. A 1-dimension structure adaptive self-organizing neural network for QAM signal classification//ICNC 2007. HaiKou: , 2007: 53-57. [4] 贺新颖, 曾志民, 郭彩丽. 基于概率密度估计的认知无线电动态频谱接入算法[J]. 北京邮电大学学报, 2009, 32(1): 108-112. He Xinying, Zeng Zhimin, Guo Caili. A dynamic spectrum access algorithm based on probability density estimation in cognitive radio [J]. Journal of Beijing University of Posts and Telecommunications, 2009, 32(1): 108-112. [5] 王翔英, 梁双春, 钟义信. 支持向量机在多用户检测中的应用[J]. 北京邮电大学学报, 2004, 27(增): 107-111. Wang Xiangying, Liang Shuangchun, Zhong Yixin. The multiuser detector using SVM in CDMA systems[J]. Journal of Beijing University of Posts and Telecommunications, 2009, 27(Sup.): 107-111. [6] 孙建成, 张太镒, 刘海员. 基于SVM的多类模拟调制方式识别算法[J]. 电子科技大学学报, 2006, 35(2): 149-152. Sun Jiancheng, Zhang Taiyi, Liu Haiyuan. Multi class analogue modulation recognition algorithms based on support vector machines[J]. Journal of University of Electronic Science and Technology of China, 2006, 35(2): 149-152. [7] 韩钢, 张文红, 李建东, 等. 基于高阶累积量和支撑矢量机的调制识别研究 [J]. 系统工程与电子技术, 2003, 25(8): 1007 -1011. Han Gang, Zhang Wenhong, Li Jiandong, et al. Study on the modulation and recognition based on the higher order cumulants and support vector machines [J]. Systems Engineering and Electronics, 2003, 25(8): 1007-1011. [8] 吕新正, 魏平, 肖先赐. 利用高阶累积量实现数字调制信号的自动识别 [J]. 电子对抗技术, 2004, 19(6): 3-6. Lv Xinzheng, Wei Ping, Xiao Xianci. Automatic identification of digital modulation signals using high order cumulants [J]. Electronic Warfare Technology, 2004, 19(6): 3-6. [9] Mika S, Ratsch G, Muller K R. A mathematical programming approach to the kernel Fisher algorithm[J]. Advances in Neural Information Processing Systems, 2001, 13: 591-597. [10] 邓乃扬, 田英杰. 支持向量机理论、算法与拓展[M]. 北京: 科学出版社, 2009: 49-55. [11] 杨国鹏. 基于核方法的高光谱影像分类与特征提取. 郑州: 信息工程大学, 2007. Yang Guopeng. Hyperspectral image classification and feature extraction based on kernel methods . Zhengzhou: Information Engineering University, 2007. [12] 荣海娜, 张葛祥, 金炜东. 系统辨识中支持向量机核函数及其参数的研究[J]. 系统仿真学报, 2006, 18(11): 3204-3208. Rong Haina, Zhang Gexiang, Jin Weidong. Selection of kernel functions and parameters for support vector machines in system identification [J]. Journal of System Simulation, 2006, 18(11): 3204-3208. [13] 闫志刚, 杜培军. 多类支持向量机推广性能分析[J]. 数据采集与处理, 2009, 24(4): 469-475. Yan Zhigang, Du Peijun. Generalization performance analysis of M-SVMs[J]. Journal of Data Acquisition & Processing, 2009, 24(4): 469-475.

核Fisher判别分析在数字信号分类中的应用

Application of Kernel Fisher Discriminant Analysis to  Digital Signal Classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	刘寅生, 段洪涛, 范振雄, 李蓉, 李景春. 基于改进MUSIC算法的短波非规则天线阵列测向系统[J]. 北京邮电大学学报, 2019, 42(5): 42-47.
[2]	赵建龙, 曲桦, 赵季红, 戴慧珺. 基于Morlet-SVR和ARIMA组合模型的网络流量预测[J]. 北京邮电大学学报, 2016, 39(2): 53-57.
[3]	刁鸣, 安春莲. 冲击噪声背景下的DOA估计新方法[J]. 北京邮电大学学报, 2013, 36(5): 99-104.
[4]	刘明骞李兵兵赵雷赵岩. 含有导频的OFDM信号子载波的调制方式识别方法[J]. 北京邮电大学学报, 2012, 35(4): 42-45.
[5]	魏宇欣. 基于KFDA-SVM的入侵检测技术（增刊）[J]. 北京邮电大学学报, 2007, 29(s1): 27-31.
[6]	周围1,2，林云1，张德民1，周正中2. 智能天线中一种上行信号空间特征盲估计算法[J]. 北京邮电大学学报, 2006, 29(6): 32-35.