降噪自编码器辅助的下行MIMO-SCMA编解码方法

doi:10.19665/j.issn1001-2400.2022.03.009

西安电子科技大学学报 ›› 2022, Vol. 49 ›› Issue (3): 74-82.doi: 10.19665/j.issn1001-2400.2022.03.009

降噪自编码器辅助的下行MIMO-SCMA编解码方法

蒋芳^1,²(),黄兴¹(),胡梦钰¹(),王翊^1,²(),许耀华^1,²(),胡艳军^1,²()

1.安徽大学计算智能与信号处理教育部重点实验室,安徽合肥 230601
2.安徽省物联网频谱感知与测试工程技术研究中心,安徽合肥 230601

收稿日期:2021-01-26 修回日期:2021-12-08 出版日期:2022-06-20 发布日期:2022-07-04
作者简介:蒋芳(1981—),女,讲师,博士,E-mail: jiangfang@ahu.edu.cn|黄兴(1998—),男,安徽大学硕士研究生,E-mail: 18815688326@163.com|胡梦钰(1996—),女,安徽大学硕士研究生,E-mail: 2331518158@qq.com|王翊(1983—),男,讲师,博士,E-mail: yiwang@ahu.edu.cn|许耀华(1976—),男,副教授,E-mail: xyh@ahu.edu.cn|胡艳军(1967—),女,教授,博士,E-mail: yanjunhu@ahu.edu.cn
基金资助:
国家自然科学基金(62071002);安徽大学博士科研启动基金

Denoising autoencoder-aided downlink MIMO-SCMA codec method

JIANG Fang^1,²(),HUANG Xing¹(),HU Mengyu¹(),WANG Yi^1,²(),XU Yaohua^1,²(),HU Yanjun^1,²()

1. Key Laboratory of Intelligent Computing & Signal Processing,Ministry of Education,Anhui University,Hefei 230601,China
2. Anhui Internet of Things Spectrum Sensing and Testing Engineering Technology Research Center,Hefei 230601,China

Received:2021-01-26 Revised:2021-12-08 Online:2022-06-20 Published:2022-07-04

摘要/Abstract

摘要：

为了改善稀疏码分多址系统在多天线应用中的误码率性能,将深度学习引入多输入多输出稀疏码分多址系统,提出了一种降噪自编码器辅助的编解码方法。发射端使用多个深度神经网络单元构建多天线稀疏码分多址编码器,通过神经网络的学习获得每个用户在不同发射天线上的码本,采用降噪自编码器的结构在输入端引入噪声层,使得编码器的输出为更具鲁棒性的特征表示;接收端设计了一个全链接的深度神经网络作为解码器,该解码器将多天线检测与多用户检测联合进行,一次解码即可获得用户数据;采用端到端的训练方式对编解码器进行训练,优化神经网络的结构与参数,使得神经网络能够快速收敛。实验结果表明,提出的编解码方法可以降低多输入多输出稀疏码分多址系统的误码率,同时减少接收端检测的时间。

关键词: 多输入多输出, 稀疏码分多址, 降噪自编码器, 深度神经网络

Abstract:

Aiming to improve the bit error rate (BER) performance of sparse code multiple access (SCMA)systems in multi-antenna applications,deep learning is introduced in a MIMO-SCMA system and a denoising autoencoder-aided Codec method (DAE-MIMO-SCMA) is proposed.Multiple deep neural network (DNN) units are used by the transmitter to construct the MIMO-SCMA encoder.The codebook of each user on different transmitting antennas is obtained through neural network (NN) learning.Moreover,the noise layer is used at the transmitter so that the output of the encoder is more robust.At the receiver is designed a fully connected DNN as a decoder,which combines multi-antenna detection and multi-user detection to obtains the original data of all users at one time.An end-to-end training method is used to train the Codec,optimizing the structure and parameters of the NN,which improves the convergent rate.Experimental results show that the proposed Codec method can lower the BER of the MIMO-SCMA system and reduce the detection time at the receiver.

Key words: multiple input multiple output, sparse code multiple access, denoising autoencoder, deep neural network

中图分类号:

TN914.5

蒋芳,黄兴,胡梦钰,王翊,许耀华,胡艳军. 降噪自编码器辅助的下行MIMO-SCMA编解码方法[J]. 西安电子科技大学学报, 2022, 49(3): 74-82.

JIANG Fang,HUANG Xing,HU Mengyu,WANG Yi,XU Yaohua,HU Yanjun. Denoising autoencoder-aided downlink MIMO-SCMA codec method[J]. Journal of Xidian University, 2022, 49(3): 74-82.

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 22

[1]	LARSSONE G, TUFVESSON F, EDFORS O, et al. Massive MIMO for Next Generation Wireless Systems[J]. IEEE Communications Magazine, 2014, 52(2):186-195.
[2]	SAITO Y, KISHIYAMA Y, BENJEBBOUR A, et al. Non-Orthogonal Multiple Access (NOMA) for Cellular Future Radio Access[C]// 2013 IEEE 77th Vehicular Technology Conference (VTC Spring).Piscataway:IEEE, 2013:1-5.
[3]	NIKOPOUR H, BALIGH H. Sparse Code Multiple Access[C]// 2013 IEEE 24th Annual International Symposium on Personal,Indoor,and Mobile Radio Communications (PIMRC).Piscataway:IEEE, 2013:332-336.
[4]	HAN S, GUO C, MENG W, et al. The Uplink and Downlink Design of MIMO-SCMA System[C]// International Wireless Communications and Mobile Computing Conference.Piscataway:IEEE, 2016:56-60.
[5]	KURNIAWAN D, ARIFIANTO M S, KURNIAWAN A. Low Complexity MIMO-SCMA Detector[C]// 2019 IEEE 5th International Conference on Wireless and Telematics (ICWT).Piscataway:IEEE, 2019:1-5.
[6]	DU Y, DONG B, CHEN Z, et al. Joint Sparse Graph-Detector Design for Downlink MIMO-SCMA Systems[J]. IEEE Wireless Communication Letters, 2017, 6(1):14-17.
[7]	MHEICH Z, HEMADEH I A, LIU Z, et al. Low-Complexity Expectation Propagation Detection for Uplink MIMO-SCMA Systems[C]// 2020 International Conference on UK-China Emerging Technologies (UCET).Piscataway:IEEE, 2020:1-4.
[8]	WANG P, LIU L, ZHOU S, et al. Near-Optimal MIMO-SCMA Uplink Detection with Low-Complexity Expectation Propagation[J]. IEEE Transactions on Wireless Communications, 2020, 19(2):1025-1037. doi: 10.1109/TWC.2019.2950314
[9]	潘志鹏, 雷菁, 文磊, 等. 高斯近似消息传播SM-SCMA多用户检测算法[J]. 西安电子科技大学学报, 2020, 47(6):37-44.
	PANG Zhipeng, LEI Jing, WEN Lei, et al. Gaussian-Approximated Message Passing Algorithm for the SM-SCMA System[J]. Journal of Xidian University, 2020, 47(6):37-44.
[10]	DAI J, NIU K, LIN J. Iterative Gaussian-Approximated Message Passing Receiver for MIMO-SCMA System[J]. IEEE Journal of Selected Topics in Signal Processing, 2019, 13(3):753-765. doi: 10.1109/JSTSP.2019.2898323
[11]	YAN C, KANG G X, ZHANGN. A Dimension Distance-Based SCMA Codebook Design[J]. IEEE Access, 2017, 5:5471-5479. doi: 10.1109/ACCESS.2017.2685618
[12]	付伟. 基于遗传算法的下行MIMO-SCMA系统码本设计[D]. 西安: 西安电子科技大学, 2018.
[13]	PAN Z P,LIUW, LEI J, et al. Multi-Dimensional Space-Time Block Coding Aided Downlink MIMO-SCMA[J]. IEEE Transactions on Vehicular Technology, 2019, 68(7):6657-6669. doi: 10.1109/TVT.2019.2915351
[14]	LU C, XU W, SHEN H, et al. An Enhanced SCMA Detector Enabled by Deep Neural Network[C]// 2018 IEEE/CIC International Conference on Communications in China (ICCC).Piscataway:IEEE, 2018:1-5.
[15]	ABIDI I, HIZEM M, AHRIZ I, et al. Convolutional Neural Networks for Blind Decoding in Sparse Code Multiple Access[C]// 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC).Piscataway:IEEE, 2019:24-28.
[16]	SAMUEL N, DISKIN T, WIESELA. Deep MIMO Detection[C]// 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).Piscataway:IEEE, 2017:1-5.
[17]	WANG T Q, WEN C K, WANG H Q, et al. Deep Learning for Wireless Physical Layer:Opportunities and Challenges[J]. China Communication, 2017, 14(11):92-111. doi: 10.1109/CC.2017.8233654
[18]	XU W H, ZHONG Z W, BEERY Y, et al. Joint Neural Network Equalizer and Decoder[C]// 2018 15th International Symposium on Wireless Communication Systems (ISWCS).Piscataway:IEEE, 2018:1-6.
[19]	O’SHEA T, HOYDIS J. An Introduction to Deep Learning for the Physical Layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2017, 3(4):563-575. doi: 10.1109/TCCN.2017.2758370
[20]	KIM M, KIM N I, LEE W, et al. Deep Learning-Aided SCMA[J]. IEEE Communications Letters, 2018, 22(4):720-723. doi: 10.1109/LCOMM.2018.2792019
[21]	HAN Y, WANG Z, GUO Q, et al. Deep Learning-Based Detection for Moderate-Density Code Multiple Access in IoT Networks[J]. IEEE Communications Letters, 2020, 24(1):122-125. doi: 10.1109/LCOMM.2019.2952392
[22]	LIN J Z, FENG S Z, ZHANG Y, et al. A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access[J]. Neurocomputing, 2020, 382:52-63. doi: 10.1016/j.neucom.2019.11.066

降噪自编码器辅助的下行MIMO-SCMA编解码方法

Denoising autoencoder-aided downlink MIMO-SCMA codec method

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 22

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	史加荣,李金红. 新型深度矩阵分解及其在推荐系统中的应用[J]. 西安电子科技大学学报, 2022, 49(3): 171-182.
[2]	曹鹏程,刘伟伟,刘光杰,茅伟伟,戴跃伟. 一种基于预编码的MIMO无线隐信道[J]. 西安电子科技大学学报, 2022, 49(2): 42-49.
[3]	王勇,王喜媛,任泽洋. 毫米波MIMO的DNN混合预编码梯度优化方法[J]. 西安电子科技大学学报, 2022, 49(1): 202-207.
[4]	张书伟,李俊民. 一种复杂监控场景下的人体检测算法[J]. 西安电子科技大学学报, 2021, 48(5): 68-77.
[5]	曹艺,蔡晓东. 一种有效的困难样本学习策略[J]. 西安电子科技大学学报, 2021, 48(3): 99-105.
[6]	刘洁怡,公茂果,詹涛,李豪,张明阳. 一种深度神经网络多站雷达系统干扰鉴别方法[J]. 西安电子科技大学学报, 2021, 48(2): 133-138.
[7]	张华,高浩然,杨兴国,李文敏,高飞,温巧燕. TargetedFool:一种实现有目标攻击的算法[J]. 西安电子科技大学学报, 2021, 48(1): 149-159.
[8]	张树栋,高海昌,曹曦文,康帅. 针对ASR系统的快速有目标自适应对抗攻击[J]. 西安电子科技大学学报, 2021, 48(1): 168-175.
[9]	常新旭,张杨,杨林,寇金桥,王昕,徐冬冬. 融合多头自注意力机制的语音增强方法[J]. 西安电子科技大学学报, 2020, 47(1): 104-110.
[10]	袁文浩,梁春燕,娄迎曦,房超,王志强. 一种时频平滑的深度神经网络语音增强方法[J]. 西安电子科技大学学报, 2019, 46(4): 130-136.
[11]	乔瑞秀,陈刚,龚国良,鲁华祥. 一种高性能可重构深度卷积神经网络加速器[J]. 西安电子科技大学学报, 2019, 46(3): 130-139.
[12]	陈晓范,申海杰,边倩,王振铎,田新志. 结合注意力机制的人脸超分辨率重建[J]. 西安电子科技大学学报, 2019, 46(3): 148-153.
[13]	袁文浩,娄迎曦,梁春燕,王志强. 感知联合优化的深度神经网络语音增强方法[J]. 西安电子科技大学学报, 2019, 46(2): 89-94.
[14]	李文刚;胡爱丽;孙珑心;王屹伟. LOS环境下零导频Massive MIMO通信方法[J]. 西安电子科技大学学报, 2018, 45(4): 1-5+85.
[15]	刘洁怡;张林让;于恒力;唐世阳; 赵珊珊. 分集MIMO雷达目标回波相关性分析[J]. 西安电子科技大学学报, 2018, 45(4): 69-74.