基于采样协方差矩阵的混合核SVM高效频谱感知

doi:10.11959/j.issn.1000-0801.2019210

电信科学 ›› 2019, Vol. 35 ›› Issue (11): 19-26.doi: 10.11959/j.issn.1000-0801.2019210

基于采样协方差矩阵的混合核SVM高效频谱感知

聂建园¹,包建荣¹,姜斌¹,刘超¹(),朱芳¹,何剑海²

¹ 杭州电子科技大学通信工程学院，浙江杭州 310018
² 宁波职业技术学院电子信息工程学院，浙江宁波 315800

修回日期:2019-08-19 出版日期:2019-11-01 发布日期:2019-12-23
作者简介:聂建园（1994- ），女，杭州电子科技大学硕士生，主要研究方向为认知无线电频谱感知、压缩感知等|包建荣（1978- ），男，博士后，杭州电子科技大学教授、博士生导师，主要研究方向为空间无线通信、通信信号处理与自主无线电等|姜斌（1980- ），男，现就职于杭州电子科技大学，主要研究方向为空间无线通信、无线传感器网络等|刘超（1977- ），男，博士，杭州电子科技大学副教授，主要研究方向为无线通信、计算机通信网等。|朱芳（1973- ），男，博士，杭州电子科技大学讲师，主要研究方向为无线通信和信息安全等。|何剑海（1979- ），男，博士，宁波职业技术学院副教授，主要研究方向为认知无线电、协同通信等。
基金资助:
浙江省自然科学基金资助项目(LY17F010019);国家自然科学基金资助项目(U1809201);浙江省公益性技术应用研究计划基金资助项目(LGG18F010011);浙江省公益性技术应用研究计划基金资助项目(LGG19F010004)

An efficient spectrum sensing of mixed kernel SVM based on sampling covariance matrix

Jianyuan NIE¹,Jianrong BAO¹,Bin JIANG¹,Chao LIU¹(),Fang ZHU¹,Jianhai HE²

¹ School of Communication Engineering,Hangzhou Dianzi University,Hangzhou 310018,China
² School of Electronic Information Engineering,Ningbo Polytechnic,Ningbo 315800,China

Revised:2019-08-19 Online:2019-11-01 Published:2019-12-23
Supported by:
Natural Science Foundation of Zhejiang Province(LY17F010019);The National Natural Science Foundation of China(U1809201);Public Welfare Technology Application Research Program of Zhejiang Province(LGG18F010011);Public Welfare Technology Application Research Program of Zhejiang Province(LGG19F010004)

摘要/Abstract

摘要：

近年来随着盲检测算法的提出，越来越多的基于采样协方差矩阵的盲检测算法应用于频谱感知。针对其检测门限是近似值，检测性能会受到影响等问题，提出了基于采样协方差矩阵的混合核函数的支持向量机（support vector machine,SVM）高效频谱感知，通过感知信号采样协方差矩阵的最大最小特征值（maximum minimum eigenvalue,MME）和协方差绝对值（covariance absolute value,CAV）提取的统计量作为SVM的特征向量并训练其生成频谱感知的分类器，无需计算检测门限并且特征提取减少了样本集的大小。利用遗传算法（genetic algorithm,GA）优化混合核函数的SVM的参数。实验结果表明，该方法比MME算法和CAV算法的检测概率有所提高，并且比SVM减少了感知时间，具有良好的实用性。

关键词: 检测门限, 混合核函数, SVM, MME, GA

Abstract:

In recent years,with the blind detection algorithms were proposed,more and more blind algorithms based on sampling covariance matrix were applied to spectrum sensing.The detection threshold was an approximation,and the detection performance would be affected for this algorithms.Thus,the mixed kernel function support vector machine (SVM) efficient spectrum sensing based on sampling covariance matrix was proposed.The statistics which were maximum minimum eigenvalue (MME) and covariance absolute value (CAV) of sensing signal sampling covariance matrices were used as the feature vectors of SVM and were trained to generate a spectrum sensing classifier.The advantage of this algorithm was that it needn’t calculate the detection threshold and the extraction of features reduces size of the sample set.The genetic algorithm (GA) was used to optimize the parameters of mixed kernel function SVM algorithm.The experimental results show that the proposed method has higher detection probability than MME and CAV algorithms,and has less sensing time than SVM,which has good practicability.

Key words: detection threshold, mixed kernel function, SVM, MME, GA

中图分类号:

TN925

聂建园,包建荣,姜斌,刘超,朱芳,何剑海. 基于采样协方差矩阵的混合核SVM高效频谱感知[J]. 电信科学, 2019, 35(11): 19-26.

Jianyuan NIE,Jianrong BAO,Bin JIANG,Chao LIU,Fang ZHU,Jianhai HE. An efficient spectrum sensing of mixed kernel SVM based on sampling covariance matrix[J]. Telecommunications Science, 2019, 35(11): 19-26.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 17

[1]	LI B , SUN M , LI X ,et al. Energy detection based spectrum sensing for cognitive radios over time-frequency doubly selective fading channels[J]. IEEE Transactions on Signal Processing, 2015,63(2): 402-417. doi: 10.1109/TSP.2014.2368996
[2]	ZHANG X , GAO F , CHAI R ,et al. Matched filter based spectrum sensing when primary user has multiple power levels[J]. China Communications, 2015,12(2): 21-31.
[3]	DU J , HUANG H , JING X J ,et al. Cyclostationary feature based spectrum sensing via low-rank and sparse decomposition in cognitive radio networks[C]// 2016 16th International Symposium on Communications and Information Technologies (ISCIT),September 26-28,2016,Qingdao,China. Piscataway:IEEE Press, 2016: 615-619.
[4]	YANG X , LEI K J . Blind detection for primary user based on the sample covariance matrix letters in cognitive radio[J]. IEEE Communications Letters, 2013,15(1): 40-42. doi: 10.1109/LCOMM.2010.111910.101278
[5]	刘顺兰, 王静, 包建荣 . 高检测概率协方差矩阵机会协作频谱感知[J]. 电信科学, 2019,35(1): 67-73.
	LIU S L , WANG J , BAO J R . Covariance matrix opportunistic cooperative spectrum sensing of high detection probability[J]. Telecommunications Science, 2019,35(1): 67-73.
[6]	LI Z , ZHOU F , SI J ,et al. Feasibly efficient cooperative spectrum sensing scheme based on Cholesky decomposition of the correlation matrix[J]. IET Communications, 2016,10(9): 1003-1011. doi: 10.1049/iet-com.2015.0654
[7]	ZHOU F , BEAULIEU N C , LI Z ,et al. Feasibility of maximum eigenvalue cooperative spectrum sensing based on Cholesky factorization[J]. IET Communications, 2016,10(2): 199-206. doi: 10.1049/iet-com.2015.0252
[8]	李有均 . 基于随机矩阵的协作频谱感知算法研究[D]. 重庆：重庆大学, 2017.
	LI Y J . Cooperative spectrum sensing algorithm based on random matrix[D]. Chongqing:Chongqing University, 2017.
[9]	PUTRI S M , SUGIHARTONO I . Energy efficiency in cognitive radio with cooperative MME (maximum to minimum eigenvalue) spectrum sensing method[C]// 2015 International Seminar on Intelligent Technology and Its Applications (ISITIA),May 20-21,2015,Surabaya,Indonesia. Piscataway:IEEE Press, 2015: 379-384.
[10]	WAEL C B A , ARMI N , ROHMAN B P A . Spectrum sensing for low SNR environment using maximum-minimum eigenvalue (MME) detection[C]// 2016 International Seminar on Intelligent Technology and Its Applications (ISITIA’16),July 28-30,2016,Lombok,Indonesia. Piscataway:IEEE Press, 2016: 435-438.
[11]	赵知劲, 胡伟康, 王海泉 . 基于双特征值极限分布的合作频谱感知算法[J]. 电信科学, 2014,30(4): 82-87.
	ZHAO Z J , HU W K , WANG H Q . Cooperative spectrum sensing algorithm based on double eigenvalue limiting distribution[J]. Telecommunications science, 2014,30(4): 82-87.
[12]	WANG F , ZHEN Z , WANG B ,et al. Comparative study on KNN and SVM based weather classification models for day ahead short term solar PV power forecasting[J]. Applied Sciences, 2018,8(1): 3-5. doi: 10.3390/app8010003
[13]	赵知劲, 陈京来 . 蜂群优化神经网络的频谱感知[J]. 信号处理, 2016,32(1): 77-82.
	ZHAO Z J , CHEN J L . A neural network spectrum sensing algorithm using bee colony optimization[J]. Signal Processing, 2016,32(1): 77-82.
[14]	聂勇, 叶翔, 翟旭平 . 基于支持向量机和噪声估计的宽带频谱感知方法[J]. 电子测量技术, 2017,40(12): 88-92.
	NIE Y , YE X , ZHAI X P . Wideband spectrum sensing method based on SVM and EN[J]. Electronic Measurement Technology, 2017,40(12): 88-92.
[15]	翟旭平, 杨兵兵, 孟田 . 基于PCA和混合核函数QPSO_SVM频谱感知算法[J]. 电子测量技术, 2016,39(9): 87-90,107.
	ZHAI X P , YANG B B , MENG T . Spectrum sensing based on PCA and QPSO_SVM with mixed kernel[J]. Electronic Measurement Technology, 2016,39(9): 87-90,107.
[16]	翟旭平, 孟田, 杨兵兵 . 基于 SOM-SVM 频谱感知算法[J]. 电子测量技术, 2016,39(10): 76-80.
	ZHAI X P , MENG T , YANG B B . Spectrum sensing algorithm based on SOM-SVM[J]. Electronic Measurement Technology, 2016,39(10): 76-80.
[17]	加尔·肯别克, 袁杰, . 变样本量学习最小二乘支持向量机算法[J]. 计算机工程, 2019,45(1): 192-198,205. doi: 10.19678/j.issn.1000-3428.0048673
	JIAE K , YUAN J . Variable samples learning least square support vector machine algorithm[J]. Computer Engineering, 2019,45(1): 192-198,205. doi: 10.19678/j.issn.1000-3428.0048673

基于采样协方差矩阵的混合核SVM高效频谱感知

An efficient spectrum sensing of mixed kernel SVM based on sampling covariance matrix

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 17

相关文章 15

Metrics

推荐阅读 0

[1]	张茜, 詹明, 章坚武, 王富龙, 冯云开, 唐浩. 一种合并状态度量计算的高效并行Turbo码译码器结构设计及FPGA实现[J]. 电信科学, 2022, 38(2): 47-58.
[2]	邱佳锋. 宽带毫米波大规模MIMO系统中低复杂度波束域信道估计[J]. 电信科学, 2020, 36(8): 122-129.
[3]	宓正宇. 基于Goldengate的数据库异地灾备实现[J]. 电信科学, 2018, 34(4): 136-143.
[4]	王兴鹏,许晓荣,胡安迪,冯维. Nakagami-m衰落信道下存在窃听攻击的认知中继网络安全性与可靠性折中方案[J]. 电信科学, 2018, 34(12): 24-32.
[5]	李光球,王占湾,任婷洁,刘帅帅. 相关衰落信道上WCDMA系统的安全性能分析[J]. 电信科学, 2018, 34(10): 9-17.
[6]	李创创,卢光跃,王航龙. 基于边界样本欠取样支持向量机的电信用户欠费分类算法[J]. 电信科学, 2017, 33(9): 85-91.
[7]	周恒,畅志贤,杨武军,郭娟. 一种5G网络切片的编排算法[J]. 电信科学, 2017, 33(8): 130-137.
[8]	赵书锋,申滨,杨芙蓉. 大规模MIMO系统低复杂度混合迭代信号检测[J]. 电信科学, 2017, 33(7): 39-46.
[9]	席孝强,兰巨龙,段通,江逸茗. SDN中一种基于拓扑变换的功能组合方法[J]. 电信科学, 2016, 32(7): 11-20.
[10]	李长水. 衰落信道上TAS/MRC的错误指数[J]. 电信科学, 2016, 32(5): 127-131.
[11]	覃远年,邹川,滕召宇. 60 GHz无线收发实验平台的探究[J]. 电信科学, 2016, 32(3): 75-80.
[12]	李扬,赵海涛,唐紫浩,张玉婷. 车辆自组织网络中基于信道传输环境的网络连通性能[J]. 电信科学, 2016, 32(12): 99-103.
[13]	李光球,董家云. Nakagami衰落上DE-QPSK在联合收发分集下的性能分析[J]. 电信科学, 2015, 31(8): 72-77.
[14]	董昊,曲桦,赵季红,陈梁骏,戴慧珺. 基于DT-KSVM的业务感知算法[J]. 电信科学, 2015, 31(11): 67-71.
[15]	杨建明,周旭文,杨波,唐斓. EPC部署IPv6策略研究[J]. 电信科学, 2014, 30(Z2): 76-81.