基于Hilbert信號(hào)空間的未知干擾自適應(yīng)識(shí)別方法

黃國策; 王桂勝; 任清華; 董淑福; 高維廷; 魏帥

doi:10.11999/JEIT180891

基于Hilbert信號(hào)空間的未知干擾自適應(yīng)識(shí)別方法

doi: 10.11999/JEIT180891

1.
空軍工程大學(xué)信息與導(dǎo)航學(xué)院西安 710077
2.
95910部隊(duì) ??酒泉 ??735000

基金項(xiàng)目: 國家自然科學(xué)基金(61701521)，中國博士后科學(xué)基金(2016M603044)，陜西省自然科學(xué)基金(2018JQ6074)

詳細(xì)信息

作者簡介:
黃國策：男，1962年生，博士，教授，研究方向?yàn)檐娛潞娇胀ㄐ拧⒍滩ńM網(wǎng)

王桂勝：男，1992年生，博士生，研究方向?yàn)檐娛潞娇胀ㄐ拧⑼ㄐ趴垢蓴_、認(rèn)知無線網(wǎng)絡(luò)

任清華：男，1967年生，教授，研究方向?yàn)檐娛潞娇胀ㄐ拧⒆儞Q域通信

董淑福：男，1971年生，教授，研究方向?yàn)檐娛潞娇胀ㄐ拧⒍滩ńM網(wǎng)

高維廷：男，1984年生，博士，研究方向?yàn)殡姶蓬l譜管理

魏帥：女，1993年生，碩士，研究方向?yàn)槎嗄繕?biāo)跟蹤識(shí)別

通訊作者:
王桂勝　wgsfuyun@163.com

中圖分類號(hào): TN92
計(jì)量
- 文章訪問數(shù): 2088
- HTML全文瀏覽量: 1028
- PDF下載量: 78
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2018-09-18
- 修回日期: 2019-03-26
- 網(wǎng)絡(luò)出版日期: 2019-04-23
- 刊出日期: 2019-08-01

Adaptive Recognition Method for Unknown Interference Based on Hilbert Signal Space

1.
College of Information and Navigation, Air Force Engineering University, Xi’an 710077, China
2.
The 95910 Troop, Jiuquan 735000, China

Funds: The National Natural Science Foundation of China (61701521), The Postdoctoral Science Foundation of China (2016M603044), The Shaanxi Province Natural Science Foundation (2018JQ6074)

摘要

摘要: 針對(duì)大樣本下未知干擾類型的分類識(shí)別問題，該文提出一種基于信號(hào)特征空間的未知干擾自適應(yīng)識(shí)別方法。首先，基于Hilbert信號(hào)空間理論對(duì)干擾信號(hào)進(jìn)行處理，建立干擾信號(hào)特征空間，進(jìn)而利用投影定理對(duì)未知干擾進(jìn)行最佳逼近，提出基于信號(hào)特征空間的概率神經(jīng)網(wǎng)絡(luò)(PNN)分類算法，并設(shè)計(jì)了未知干擾分類識(shí)別器的處理流程。仿真結(jié)果表明，與兩種傳統(tǒng)方法相比，該方法在已知干擾的分類精度方面分別提高了12.2%和2.8%；滿足條件的未知干擾最佳逼近效果隨功率強(qiáng)度呈線性變化，設(shè)計(jì)的分類識(shí)別器在滿足最佳逼近的各類干擾中總體識(shí)別率達(dá)到91.27%，處理干擾識(shí)別的速度明顯改善；在信噪比達(dá)到4 dB時(shí)，對(duì)未知干擾識(shí)別準(zhǔn)確率達(dá)到92%以上。
- 無人機(jī)通信 /
- 未知干擾 /
- 自適應(yīng)識(shí)別 /
- Hilbert信號(hào)空間 /
- 概率神經(jīng)網(wǎng)絡(luò)
Abstract: In order to solve the problem of classification and recognition of unknown interference types under large samples, an adaptive recognition method for unknown interference based on signal feature space is proposed. Firstly, the interference signal is processed and the interference signal feature space is established with the Hilbert signal space theory. Then the projection theorem is used to approximate the unknown interference. The classification algorithm based on signal feature space with Probabilistic Neural Network (PNN) is proposed, and the processing flow of unknown interference classifier is designed. The simulation results show that compared with two kinds of traditional methods, the proposed method improves the classification accuracy of the known interference by 12.2% and 2.8% respectively. The optimal approximation effect of the unknown interference varies linearly with the power intensity in the condition, and the overall recognition rate of the designed classifier reaches 91.27% in the various types of interference satisfying the optimal approximation, and the speed of processing interference recognition is improved significantly. When the signal-to-noise ratio reaches 4 dB, the accuracy of unknown interference recognition is more than 92%.
- Unmanned aerial vehicle communications /
- Unknown interference /
- Adaptive recognition /
- Hilbert signal space /
- Probabilistic Neural Network (PNN)

HTML全文

圖 1 基于信號(hào)特征空間的概率神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)圖

下載: 全尺寸圖片幻燈片

圖 2 干擾分類處理流程圖

下載: 全尺寸圖片幻燈片

圖 3 不同干擾功率下最佳逼近均方根誤差圖

下載: 全尺寸圖片幻燈片

圖 4 不同信噪比下本文多分類算法識(shí)別率

下載: 全尺寸圖片幻燈片

表 1 干擾信號(hào)參數(shù)

干擾類型	干擾參數(shù)	數(shù)值
單音干擾	干擾頻點(diǎn)(MHz)	150
多音干擾	干擾頻點(diǎn)(MHz)	50, 100, ···, 250
部分頻帶干擾	覆蓋帶寬(MHz)	250～400
脈沖干擾	占空比(%)	10
線性調(diào)頻干擾 (單分量)	初始頻率(MHz)	150
線性調(diào)頻干擾 (單分量)	調(diào)頻率	500
梳狀譜干擾	分量數(shù)目	3
梳狀譜干擾	帶寬(MHz)	800

下載: 導(dǎo)出CSV

表 2 干擾分類算法識(shí)別率比較

信號(hào)空間數(shù)據(jù)集	識(shí)別率(%)
信號(hào)空間數(shù)據(jù)集	單音干擾	多音干擾	部分頻帶	線性調(diào)頻	脈沖干擾	梳狀譜	總體識(shí)別率
傳統(tǒng)SVM分類器	85.0	98.7	100	82.5	90	81.2	86.3
文獻(xiàn)[12]	100	98.7	100	98.7	100	98.7	95.7
本文算法	100	100	100	91.0	100	100	98.5

下載: 導(dǎo)出CSV

表 3 多分類算法性能比較(%)

干擾空間數(shù)據(jù)集	分類識(shí)別率		訓(xùn)練識(shí)別率		測(cè)試識(shí)別率
干擾空間數(shù)據(jù)集	本文算法	傳統(tǒng)算法	本文算法	傳統(tǒng)算法	本文算法	傳統(tǒng)算法
單音干擾	92.41	47.55	92.59	50.85	91.27	46.24
多音干擾	98.73	45.37
部分頻帶	81.01	45.99
線性調(diào)頻	100	45.37
脈沖干擾	74.36	45.86
梳狀譜	98.72	46.94
未知干擾	93.59	46.62

下載: 導(dǎo)出CSV

參考文獻(xiàn)(21)

POISEL R A. Modern Communications Jamming Principles and Techniques[M]. Boston: Artech House, 2011: 279–288.

HU Su, BI Guoan, GUAN Yongliang, et al. TDCS-based cognitive radio networks with multiuser interference avoidance[J]. IEEE Transactions on Communications, 2013, 61(12): 4828–4835. doi: 10.1109/TCOMM.2013.111313.130261

ERHAN D, SZEGEDY C, TOSHEV A, et al. Scalable object detection using deep neural networks[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2155–2162. doi: 10.1109/CVPR.2014.276.

OQUAB M, BOTTOU L, LAPTEV I, et al. Learning and transferring mid-level image representations using convolutional neural networks[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 1717–1724. doi: 10.1109/CVPR.2014.222.

WATT N and DU PLESSIS M C. Dropout algorithms for recurrent neural networks[C]. The Annual Conference of the South African Institute of Computer Scientists and Information Technologists, Port Elizabeth, South Africa, 2018: 72–78. doi: 10.1145/3278681.3278691.

WANG Shangxing, LIU Hanpeng, GOMES P H, et al. Deep reinforcement learning for dynamic multichannel access in wireless networks[J]. IEEE Transactions on Cognitive Communications and Networking, 2018, 4(2): 257–265. doi: 10.1109/TCCN.2018.2809722

張彪, 閆曉鵬, 栗蘋, 等. 基于支持向量機(jī)的無線電引信抗掃頻式干擾研究[J]. 兵工學(xué)報(bào), 2016, 37(4): 635–640. doi: 10.3969/j.issn.1000-1093.2016.04.009

ZHANG Biao, YAN Xiaopeng, LI Ping, et al. Research on anti-frequency sweeping jamming of radio fuze based on support vector machine[J]. Acta Armamentarii, 2016, 37(4): 635–640. doi: 10.3969/j.issn.1000-1093.2016.04.009

王國宏, 白杰, 張翔宇, 等. 基于FRFT域特征差異的壓制干擾檢測(cè)與分類算法[J]. 北京航空航天大學(xué)學(xué)報(bào), 2018, 44(6): 1124–1132. doi: 10.13700/j.bh.1001-5965.2017.0423

WANG Guohong, BAI Jie, ZHANG Xiangyu, et al. Detection and classification algorithm of suppression interference based on characteristic differences of FRFT domain[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(6): 1124–1132. doi: 10.13700/j.bh.1001-5965.2017.0423

劉明騫, 李兵兵, 曹超鳳, 等. 認(rèn)知無線電中非高斯噪聲下數(shù)字調(diào)制信號(hào)識(shí)別方法[J]. 通信學(xué)報(bào), 2014, 35(1): 82–88. doi: 10.3969/j.issn.1000-436x.2014.01.010

LIU Mingqian, LI Bingbing, CAO Chaofeng, et al. Recognition method of digital modulation signals over non-Gaussian noise in cognitive radio[J]. Journal on Communications, 2014, 35(1): 82–88. doi: 10.3969/j.issn.1000-436x.2014.01.010

YANG Zeyi, TAO Ran, WANG Yue, et al. A novel multi-carrier order division multi-access communication system based on TDCS with fractional Fourier transform scheme[J]. Wireless Personal Communications, 2014, 79(2): 1301–1320. doi: 10.1007/s11277-014-1931-8

KUZOVNIKOV A V. Study of the methods for developing jamming-immune communications systems with the use of wavelet-modulated signals[J]. Journal of Communications Technology and Electronics, 2014, 59(1): 61–70. doi: 10.1134/S1064226914010069

王桂勝, 任清華, 姜志剛, 等. 基于信號(hào)特征空間的TDCS干擾分類識(shí)別[J]. 系統(tǒng)工程與電子技術(shù), 2017, 39(9): 1950–1958. doi: 10.3969/j.issn.1001-506X.2017.09.06

WANG Guisheng, REN Qinghua, JIANG Zhigang, et al. Jamming classification and recognition in transform domain communication system based on signal feature space[J]. Systems Engineering and Electronics, 2017, 39(9): 1950–1958. doi: 10.3969/j.issn.1001-506X.2017.09.06

TAO Chao, PAN Hongbo, LI Yansheng, et al. Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(12): 2438–2442. doi: 10.1109/LGRS.2015.2482520

郭立民, 寇韻涵, 陳濤, 等. 基于棧式稀疏自編碼器的低信噪比下低截獲概率雷達(dá)信號(hào)調(diào)制類型識(shí)別[J]. 電子與信息學(xué)報(bào), 2018, 40(4): 875–881. doi: 10.11999/JEIT170588

GUO Limin, KOU Yunhan, CHEN Tao, et al. Low probability of intercept radar signal recognition based on stacked sparse auto-encoder[J]. Journal of Electronics &Information Technology, 2018, 40(4): 875–881. doi: 10.11999/JEIT170588

DONOHO D L, TSAIG Y, DRORI I, et al. Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2012, 58(2): 1094–1121. doi: 10.1109/TIT.2011.2173241

王磊, 周樂囡, 姬紅兵, 等. 一種面向信號(hào)分類的匹配追蹤新方法[J]. 電子與信息學(xué)報(bào), 2014, 36(6): 1299–1306. doi: 10.3724/SP.J.1146.2013.00942

WANG Lei, ZHOU Lenan, JI Hongbing, et al. A new matching pursuit algorithm for signal classification[J]. Journal of Electronics &Information Technology, 2014, 36(6): 1299–1306. doi: 10.3724/SP.J.1146.2013.00942

GONZáLEZ-CAMACHO J M, CROSSA J, PéREZ-RODRíGUEZ P, et al. Genome-enabled prediction using probabilistic neural network classifiers[J]. BMC Genomics, 2016, 17: 208. doi: 10.1186/s12864-016-2553-1

張國亮, 楊春玲, 王暕來. 基于優(yōu)化概率神經(jīng)網(wǎng)絡(luò)和紅外多光譜融合的大氣層外空間彈道目標(biāo)識(shí)別[J]. 電子與信息學(xué)報(bào), 2014, 36(4): 896–902. doi: 10.3724/SP.J.1146.2013.00623

ZHANG Guoliang, YANG Chunling, and WANG Jianlai. Discrimination of exo-atmospheric targets based on optimization of probabilistic neural network and IR multispectral fusion[J]. Journal of Electronics &Information Technology, 2014, 36(4): 896–902. doi: 10.3724/SP.J.1146.2013.00623

GIRYES R and NEEDELL D. Near oracle performance and block analysis of signal space greedy methods[J]. Journal of Approximation Theory, 2015, 194: 157–174. doi: 10.1016/j.jat.2015.02.007

GIRYES R and NEEDELL D. Greedy signal space methods for incoherence and beyond[J]. Applied and Computational Harmonic Analysis, 2015, 39(1): 1–20. doi: 10.1016/j.acha.2014.07.004

胡廣書. 數(shù)字信號(hào)處理—理論、算法與實(shí)現(xiàn)[M]. 第3版, 北京: 清華大學(xué)出版社, 2012: 169–175.

HU Guangshu. Digital Signal Processing—Theory, Algorithm and Implementation[M]. 3rd ed, Beijing: Tsinghua University Press, 2012: 169–175.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)