基于ICA和特征提取的MIMO信号调制识别算法

张天骐; 范聪聪; 葛宛营; 张天

doi:10.11999/JEIT190320

基于ICA和特征提取的MIMO信号调制识别算法

doi: 10.11999/JEIT190320

重庆邮电大学通信与信息工程学院重庆 400065

基金项目: 国家自然科学基金(61671095, 61702065, 61701067, 61771085)，信号与信息处理重庆市市级重点实验室建设项目(CSTC2009CA2003)，重庆市研究生科研创新项目(CYS17219)，重庆市教育委员会科研项目(KJ1600427, KJ1600429)

详细信息

作者简介:
张天骐：男，1971年生，博士后，教授，主要研究方向为语音信号处理、通信信号的调制解调、盲处理、神经网络实现以及FPGA, VLSI 实现

范聪聪：男，1995年生，硕士生，研究方向为通信信号的盲处理

葛宛营：男，1994年生，硕士生，研究方向为语音增强与盲分离

张天：男，1993年生，硕士生，研究方向为语音信号处理，声乐分离

通讯作者:
范聪聪　2669432120@qq.com

中图分类号: TN911.7
计量
- 文章访问数: 2085
- HTML全文浏览量: 809
- PDF下载量: 112
- 被引次数: 0
出版历程
- 收稿日期: 2019-05-06
- 修回日期: 2020-03-18
- 网络出版日期: 2020-06-26
- 刊出日期: 2020-09-27

MIMO Signal Modulation Recognition Algorithm Based on ICA and Feature Extraction

School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Funds: The National Natural Science Foundation of China (61671095, 61702065, 61701067, 61771085), The Project of Key Laboratory of Signal and Information Processing of Chongqing (CSTC2009CA2003), The Chongqing Graduate Research and Innovation Project (CYS17219), The Research Project of Chongqing Educational Commission (KJ1600427, KJ1600429)

摘要

摘要: 针对非协作通信中多输入多输出(MIMO)信号的盲调制识别，该文提出一种基于独立分量分析(ICA)和特征提取的调制识别算法。根据空分复用MIMO系统各发送天线上信号的独立性，利用ICA算法从接收的混合信号中分离出发射信号。为实现全盲条件下的调制识别，在进行ICA分离前，利用最小描述长度(MDL)准则估计发射天线数。在得到发射信号之后，首先利用6阶累积量、循环谱和4次方谱算法构造4个特征参数，然后利用分层结构的神经网络分类器识别信号的调制类型。仿真结果表明，所提方法可在较低信噪比下对{2PSK, 2ASK, 2FSK, 4PSK, 4ASK, MSK, 8PSK, 16QAM}8种MIMO信号进行有效识别，当发送天线数为2、接收天线数为5、信噪比为2 dB时，识别率可达到98%以上。
- 信号处理 /
- 多输入多输出信号 /
- 独立分量分析 /
- 6阶累积量 /
- 循环谱 /
- 神经网络
Abstract: For blind modulation recognition of Multiple Input Multiple Output (MIMO) signals in non-cooperative communication, a modulation recognition method based on Independent Component Analysis (ICA) and feature extraction is proposed. According to the signal independence of each transmitting antenna in space division multiplexing MIMO system, the ICA algorithm is used to separate the transmitting signal from the received mixed signal. In order to realize modulation recognition under completely blind condition, the Minimum Description Length (MDL) criterion is used to estimate the number of transmitting antennas before ICA separation. After obtaining the transmitted signal, four characteristic parameters are constructed by using six-order cumulant, cyclic spectrum and fourth-power spectrum algorithm, and then the modulation type of the signal is identified by using hierarchical neural network classifier. The simulation results show that the proposed method can effectively recognize {2PSK, 2ASK, 2FSK, 4PSK, 4ASK, MSK, 8PSK, 16QAM} eight MIMO signals at low SNR. When the number of transmitting antennas is 2, the number of receiving antennas is 5 and the SNR is 2dB, the recognition rate can reach more than 98%.
- Signal processing /
- Multiple Input Multiple Output (MIMO) signals /
- Independent Component Analysis (ICA) /
- Sixth-order cumulant /
- Cyclic spectrum /
- Neural network

HTML全文

图 1 分层结构的神经网络分类器

下载: 全尺寸图片幻灯片

图 2 调制识别流程图

下载: 全尺寸图片幻灯片

图 3 不同${N_{\rm{t}}} \times {N_{\rm{r}}}$下的估计性能

下载: 全尺寸图片幻灯片

图 4 不同调制方式下${N_{\rm{t}}}$的估计性能

下载: 全尺寸图片幻灯片

图 5 特征参数T₁随SNR的变化曲线

下载: 全尺寸图片幻灯片

图 6 特征参数T₂随SNR的变化曲线

下载: 全尺寸图片幻灯片

图 7 特征参数T₃随SNR的变化曲线

下载: 全尺寸图片幻灯片

图 8 特征参数T₄随SNR的变化曲线

下载: 全尺寸图片幻灯片

表 1 各调制信号的高阶累积量

累积量	2PSK	4PSK	8PSK	2ASK	4ASK	2FSK	MSK	16QAM
$\left\| {{C_{21}}} \right\|$	1	1	1	1	1	1	1	1
$\left\| {{C_{42}}} \right\|$	2	1	1	2	1.36	1	1	0.68
$\left\| {{C_{63}}} \right\|$	13	4	4	13	9.16	4	4	2.08

下载: 导出CSV

表 2 ${N_{\rm{t}}} \times {N_{\rm{r}}} = 4 \times 5$时的识别率(%)

调制类型	–2 dB	0 dB	2 dB	4 dB	6 dB	8 dB	10 dB
2PSK	80.6	85.7	89.5	94.0	97.0	98.8	100
2ASK	82.4	87.3	92.0	95.2	97.0	99.3	100
2FSK	89.0	93.0	94.8	97.3	100	100	100
4PSK	89.4	93.0	96.9	98.2	98.8	100	100
4ASK	85.0	87.0	90.2	96.0	100	100	100
MSK	88.5	92.4	96.0	98.3	99.5	100	100
8PSK	91.0	95.0	97.8	99.0	100	100	100
16QAM	87.0	92.3	95.6	98.2	100	100	100

下载: 导出CSV

表 3 ${N_{\rm{t}}} \times {N_{\rm{r}}} = 4 \times 6$时的识别率(%)

调制类型	-2 dB	0 dB	2 dB	4 dB	6 dB	8 dB	10 dB
2PSK	83.7	88.0	95.0	98.2	99.4	100	100
2ASK	84.5	90.3	96.0	98.4	100	100	100
2FSK	91.3	96.0	98.2	99.5	100	100	100
4PSK	91.6	96.4	97.5	100	100	100	100
4ASK	89.0	94.4	98.0	99.2	100	100	100
MSK	91.0	95.0	97.3	100	100	100	100
8PSK	93.0	97.2	99.3	100	100	100	100
16QAM	91.0	95.3	98.4	100	100	100	100

下载: 导出CSV

表 4 ${N_{\rm{t}}} \times {N_{\rm{r}}}{\rm{ = 2}} \times {\rm{5}}$时的识别率(%)

调制类型	-2 dB	0 dB	2 dB	4 dB	6 dB	8 dB	10 dB
2PSK	89.0	93.1	98.3	99.0	100	100	100
2ASK	91.6	95.0	98.2	99.0	100	100	100
2FSK	93.4	98.3	99.5	100	100	100	100
4PSK	95.8	98.3	100	100	100	100	100
4ASK	92.0	97.0	99.6	100	100	100	100
MSK	94.0	97.6	98.8	100	100	100	100
8PSK	96.8	99.3	100	100	100	100	100
16QAM	94.3	98.0	100	100	100	100	100

下载: 导出CSV

参考文献(16)

ZHAO Yong, XU Yitao, JIANG Han, et al. Recognition of digital modulation signals based on high-order cumulants[C]. 2015 International Conference on Wireless Communications & Signal Processing, Nanjing, China, 2015: 1–5. doi: 10.1109/WCSP.2015.7341279.

郭立民, 寇韵涵, 陈涛, 等. 基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别[J]. 电子与信息学报, 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

陈涛, 柳立志, 郭立民. 基于MWC压缩采样宽带接收机的雷达信号脉内调制识别[J]. 电子与信息学报, 2018, 40(4): 867–874. doi: 10.11999/JEIT170612

CHEN Tao, LIU Lizhi, and GUO Limin. Intra-pulse modulation recognition of radar signals based on MWC compressed sampling wideband receiver[J]. Journal of Electronics &Information Technology, 2018, 40(4): 867–874. doi: 10.11999/JEIT170612

张利, 李青. 基于高阶累积量的调制识别算法的研究[J]. 信息工程大学学报, 2017, 18(4): 403–408. doi: 10.3969/j.issn.1671-0673.2017.04.005

ZHANG Li and LI Qing. Research on modulation recognition algorithm based on higher-order cumulant[J]. Journal of Information Engineering University, 2017, 18(4): 403–408. doi: 10.3969/j.issn.1671-0673.2017.04.005

谭晓衡, 褚国星, 张雪静, 等. 基于高阶累积量和小波变换的调制识别算法[J]. 系统工程与电子技术, 2018, 40(1): 171–177. doi: 10.3969/j.issn.1001-506X.2018.01.25

TAN Xiaoheng, CHU Guoxing, ZHANG Xuejing, et al. Modulation recognition algorithm based on high - order cumulants and wavelet transform[J]. Systems Engineering and Electronics, 2018, 40(1): 171–177. doi: 10.3969/j.issn.1001-506X.2018.01.25

赵雄文, 郭春霞, 李景春. 基于高阶累积量和循环谱的信号调制方式混合识别算法[J]. 电子与信息学报, 2016, 38(3): 674–680. doi: 10.11999/JEIT150747

ZHAO Xiongwen, GUO Chunxia, and LI Jingchun. Mixed recognition algorithm for signal modulation schemes by high-order cumulants and cyclic spectrum[J]. Journal of Electronics &Information Technology, 2016, 38(3): 674–680. doi: 10.11999/JEIT150747

CHOQUEUSE V, AZOU S, YAO K, et al. Blind modulation recognition for MIMO systems[J]. MTA Review, 2009, 19(2): 183–196.

张路平, 王建新. MIMO信号调制方式盲识别[J]. 应用科学学报, 2012, 30(2): 135–140. doi: 10.3969/j.issn.0255-8297.2012.02.005

ZHANG Luping and WANG Jianxin. Blind modulation recognition for MIMO signals[J]. Journal of Applied Sciences, 2012, 30(2): 135–140. doi: 10.3969/j.issn.0255-8297.2012.02.005

DAS D, BORA P K, and BHATTACHARJEE R. Blind modulation recognition of the lower order PSK signals under the MIMO Keyhole channel[J]. IEEE Communications Letters, 2018, 22(9): 1834–1837. doi: 10.1109/LCOMM.2018.2853638

WEI Mengchuan, WEI Zaixue, YANG Jianyi, et al. Automatic modulation recognition of digital signal based on auto-encoding network in MIMO System[C]. The 18th IEEE International Conference on Communication Technology, Chongqing, China, 2018: 1017–1021. doi: 10.1109/ICCT.2018.8600148.

LIU Xiaokai, ZHAO Chenglin, WANG Pengbiao, et al. Blind modulation classification algorithm based on machine learning for spatially correlated MIMO system[J]. IET Communications, 2017, 11(7): 1000–1007. doi: 10.1049/iet-com.2015.1222

COMON P and JUTTEN C. Handbook of Blind Source Separation: Independent Component Analysis and Applications[M]. Oxford: Academic Press, 2010: 147–153.

许宏吉, 刘琚, 谷波, 等. 空时分组码通信中的一类ICA盲检测方案[J]. 通信学报, 2007, 28(6): 12–19. doi: 10.3321/j.issn:1000-436X.2007.06.003

XU Hongji, LIU Ju, GU Bo, et al. ICA based blind detection scheme in space-time block coding communications[J]. Journal on Communications, 2007, 28(6): 12–19. doi: 10.3321/j.issn:1000-436X.2007.06.003

WANG Rui. Research on digital signal modulation recognition and parameter estimation based on cyclostationarity[D]. [Master dissertation], University of Electronic Science and Technology, 2012: 20–24.

REYNALDI A, LUKAS S, and MARGARETHA H. Backpropagation and Levenberg-Marquardt algorithm for training finite element neural network[C]. The 6th UKSim/AMSS European Symposium on Computer Modeling and Simulation, Valetta, Malta, 2012: 89–94. doi: 10.1109/EMS.2012.56.

KHOSRAVIANI M, KALBKHANI H, and SHAYESTEH M G. Digital modulation recognition in MIMO systems based on segmentation of received data[C]. 2017 Iranian Conference on Electrical Engineering, Tehran, Iran, 2017: 1998–2002. doi: 10.1109/IranianCEE.2017.7985384.

施引文献

资源附件(0)

访问统计