高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于多层双向长短时记忆网络的水声多载波通信索引检测方法

朱雨男 解方彤 张明亮 王彪 葛慧林

朱雨男, 解方彤, 张明亮, 王彪, 葛慧林. 基于多层双向长短时记忆网络的水声多载波通信索引检测方法[J]. 电子与信息学报, 2022, 44(6): 1984-1990. doi: 10.11999/JEIT210949
引用本文: 朱雨男, 解方彤, 张明亮, 王彪, 葛慧林. 基于多层双向长短时记忆网络的水声多载波通信索引检测方法[J]. 电子与信息学报, 2022, 44(6): 1984-1990. doi: 10.11999/JEIT210949
ZHU Yunan, XIE Fangtong, ZHANG Mingliang, WANG Biao, GE Huilin. Index Detection for Underwater Acoustic Multi-carrier Communication Based on Deep Bidirectional Long Short-term Memory Network[J]. Journal of Electronics & Information Technology, 2022, 44(6): 1984-1990. doi: 10.11999/JEIT210949
Citation: ZHU Yunan, XIE Fangtong, ZHANG Mingliang, WANG Biao, GE Huilin. Index Detection for Underwater Acoustic Multi-carrier Communication Based on Deep Bidirectional Long Short-term Memory Network[J]. Journal of Electronics & Information Technology, 2022, 44(6): 1984-1990. doi: 10.11999/JEIT210949

基于多层双向长短时记忆网络的水声多载波通信索引检测方法

doi: 10.11999/JEIT210949
基金项目: 国家自然科学基金(52071164),江苏省研究生科研与实践创新计划项目(KYCX20_3161)
详细信息
    作者简介:

    朱雨男:男,1996年生,博士生,研究方向为水声通信与深度学习

    解方彤:女,1996年生,硕士生,研究方向为水声通信

    张明亮:男,1995年生,硕士生,研究方向为水声通信

    王彪:男,1980年生,教授,研究方向为水下阵列信号处理、水声通信与水下传感器网络

    葛慧林:男,1989年生,助理研究员,研究方向为水下目标跟踪

    通讯作者:

    王彪 wangbiao@just.edu.cn

  • 中图分类号: TN929.3; TB56

Index Detection for Underwater Acoustic Multi-carrier Communication Based on Deep Bidirectional Long Short-term Memory Network

Funds: The National Natural Science Foundation of China (52071164), The Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX20_3161)
  • 摘要: 索引调制滤波器组多载波(FBMC-IM)水声通信系统在进行信号检测时,需要先根据均衡后子载波上承载的恢复数据判断出活跃子载波的位置。针对传统检测方法估计索引信息时计算复杂度高且准确度较低的问题,该文结合双向长短时记忆网络(BLSTM)对时序信号进行特征提取的优势,将深度学习理论引入水声信号处理的概念,提出一种基于多层BLSTM的水声通信信号索引检测方法。该方法将传统索引检测问题转化为数据驱动的多元分类问题,在提高估计性能的同时降低了计算复杂度。基于湖试测得的水声信道数据仿真验证了该方法的优越性和鲁棒性,可以作为索引调制机制下的一种通用检测手段。
  • 图  1  FBMC-IM系统发送端框图

    图  2  BLSTM结构图

    图  3  基于多层BLSTM的索引检测框图

    图  4  基于BLSTM索引检测的FBMC-IM系统误码率性能

    图  5  不同模式下的BLSTM索引检测性能

    表  1  $ (K,L) = (4,2) $索引调制映射表

    组合序号$ {p_1} $$ {I_g} $${{\boldsymbol{x}}_g}$one-hot标签
    $ {C_1} $00$ \{ 1,2\} $${[{s_g}(1),{s_g}(2),0,0]^{\rm{T}}}$[1,0,0,0]
    $ {C_2} $01$ \{ 1,3\} $${[{s_g}(1),0,{s_g}(2),0]^{\rm{T}}}$[0,1,0,0]
    $ {C_3} $10$ \{ 1,4\} $${[{s_g}(1),0,0,{s_g}(2)]^{\rm{T}}}$[0,0,1,0]
    $ {C_4} $11$ \{ 2,3\} $${[0,{s_g}(1),{s_g}(2),0]^{\rm{T}}}$[0,0,0,1]
    $ {C_5} $${[0,{s_g}(1),0,{s_g}(2)]^{\rm{T}}}$
    $ {C_6} $${[0,0,{s_g}(1),{s_g}(2)]^{\rm{T}}}$
    下载: 导出CSV

    表  2  索引检测算法复杂度对比

    算法名称复杂度
    ML检测$ O({2^{{p_1}}}{Q^L}) $
    ED检测$ O(K) $
    LLR检测$ O(KQ) $
    BLSTM检测$ O({2^{{p_1}}}) $
    下载: 导出CSV

    表  3  各信噪比下活跃子载波位置检测误索引率(IER)

    载波状态与检测方法0 dB5 dB10 dB15 dB20 dB25 dB30 dB
    $ (K,L) = (4,1) $, ED0.15980.09300.07270.05900.05000.04570.0445
    $ (K,L) = (4,1) $, LLR0.14920.10160.07700.06090.05200.04800.0445
    $ (K,L) = (4,1) $, BLSTM0.15790.10300.07540.05710.04220.03300.0304
    $ (K,L) = (4,2) $, ED0.24450.16020.11250.09490.08870.07850.0742
    $ (K,L) = (4,2) $, LLR0.24100.16290.12190.10040.08670.08090.0742
    $ (K,L) = (4,2) $, BLSTM0.22090.13800.09880.07800.06310.05450.0493
    $ (K,L) = (4,3) $, ED0.29340.18870.14730.12190.10860.10000.0965
    $ (K,L) = (4,3) $, LLR0.28710.19840.14650.12070.10510.09570.0949
    $ (K,L) = (4,3) $, BLSTM0.29280.18790.12900.10460.09190.08090.0770
    下载: 导出CSV

    表  4  $ (K,L) = (4,1) $时不同$ \alpha $值的EGF滤波器组系统误索引率(IER)

    载波状态与检测方法0 dB5 dB10 dB15 dB20 dB25 dB30 dB
    $ \alpha = 1/2 $, ED0.18100.13320.10860.09410.09060.08790.0871
    $ \alpha = 1/2 $, LLR0.17810.12930.11290.09960.09100.08590.0848
    $ \alpha = 1/2 $, BLSTM0.20470.14580.12880.11530.10940.10090.0898
    $ \alpha = 1 $, ED0.17270.10980.08910.07300.06650.05490.0535
    $ \alpha = 1 $, LLR0.16880.11950.08480.07210.05660.05550.0531
    $ \alpha = 1 $, BLSTM0.18370.12310.09150.07400.06010.05390.0467
    $ \alpha = 2 $, ED0.16370.11020.07970.06680.06330.05430.0520
    $ \alpha = 2 $, LLR0.15900.10430.08400.07030.05860.05430.0527
    $ \alpha = 2 $, BLSTM0.16840.11500.08980.07030.05390.04670.0406
    下载: 导出CSV
  • [1] LI Jianghui. Advanced OFDM receivers for underwater acoustic communications[D]. [Ph. D. dissertation], University of York, 2016.
    [2] HAN Jing, ZHANG Lingling, ZHANG Qunfei, et al. Low-complexity equalization of orthogonal signal-division multiplexing in doubly-selective channels[J]. IEEE Transactions on Signal Processing, 2019, 67(4): 915–929. doi: 10.1109/TSP.2018.2887191
    [3] AMINI P, CHEN Rongrong, and FARHANG-BOROUJENY B. Filterbank multicarrier communications for underwater acoustic channels[J]. IEEE Journal of Oceanic Engineering, 2015, 40(1): 115–130. doi: 10.1109/JOE.2013.2291139
    [4] 王彪, 方涛, 戴跃伟. 时间反转滤波器组多载波水声通信方法[J]. 声学学报, 2020, 45(1): 38–44. doi: 10.15949/j.cnki.0371-0025.2020.01.004

    WANG Biao, FANG Tao, and DAI Yuewei. Method of time reversal filter bank multicarrier underwater acoustic communication[J]. Acta Acustica, 2020, 45(1): 38–44. doi: 10.15949/j.cnki.0371-0025.2020.01.004
    [5] BAŞAR E, AYGÖLÜ Ü, PANAYIRCI E, et al. Orthogonal frequency division multiplexing with index modulation[J]. IEEE Transactions on Signal Processing, 2013, 61(22): 5536–5549. doi: 10.1109/TSP.2013.2279771
    [6] WEN Miaowen, CHENG Xiang, YANG Liuqing, et al. Index modulated OFDM for underwater acoustic communications[J]. IEEE Communications Magazine, 2016, 54(5): 132–137. doi: 10.1109/MCOM.2016.7470947
    [7] ABU-ALHIGA R and HAAS H. Subcarrier-index modulation OFDM[C]. The 2009 IEEE 20th International Symposium on Personal, Indoor and Mobile Radio Communications, Tokyo, Japan, 2009: 177–181.
    [8] ZHANG Jian, ZHAO Minjian, ZHONG Jie, et al. Optimised index modulation for filter bank multicarrier system[J]. IET Communications, 2017, 11(4): 459–467. doi: 10.1049/iet-com.2016.0564
    [9] 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
    [10] YE Hao, LIANG Le, LI G Y, et al. Deep learning-based end-to-end wireless communication systems with conditional GANs as unknown channels[J]. IEEE Transactions on Wireless Communications, 2020, 19(5): 3133–3143. doi: 10.1109/TWC.2020.2970707
    [11] ZHU Yunan, WANG Biao, ZHANG Youwen, et al. Convolutional neural network based filter bank multicarrier system for underwater acoustic communications[J]. Applied Acoustics, 2021, 177: 107920. doi: 10.1016/j.apacoust.2021.107920
    [12] GAO Xuanxuan, JIN Shi, WEN Chaokai, et al. ComNet: Combination of deep learning and expert knowledge in OFDM receivers[J]. IEEE Communications Letters, 2018, 22(12): 2627–2630. doi: 10.1109/LCOMM.2018.2877965
    [13] 陈友淦, 许肖梅. 人工智能技术在水声通信中的研究进展[J]. 哈尔滨工程大学学报, 2020, 41(10): 1536–1544. doi: 10.11990/jheu.202007110

    CHEN Yougan and XU Xiaomei. Research progress in artificial intelligence technology for underwater acoustic communications[J]. Journal of Harbin Engineering University, 2020, 41(10): 1536–1544. doi: 10.11990/jheu.202007110
  • 加载中
图(5) / 表(4)
计量
  • 文章访问数:  1077
  • HTML全文浏览量:  366
  • PDF下载量:  88
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-09-07
  • 修回日期:  2021-11-11
  • 录用日期:  2021-11-18
  • 网络出版日期:  2021-11-25
  • 刊出日期:  2022-06-21

目录

    /

    返回文章
    返回