基于轻量化分布式学习的自动调制分类方法

doi:10.11959/j.issn.1000-436x.2022145

Abstract

Abstract:

In order to solve the problems in centralized learning, a lightweight decentralized learning-based AMC method was proposed.By the proposed decentralized learning, a global model was trained through local training and model weight sharing, which made full use of the dataset of each communication nodes and avoided the user data leakage.The proposed lightweight network was stacked by a number of different lightweight neural network blocks with a relatively low space complexity and time complexity, and achieved a higher recognition accuracy compared with traditional DL models, which could effectively solve the problems of computing power and storage space limitation of edge devices and high communication overhead in decentralized learning based AMC method.The experimental results show that the classification accuracy of the proposed method is 62.41% based on RadioML.2016.10 A.Compared with centralized learning, the training efficiency is nearly 5 times higher with a slight classification accuracy loss (0.68%).In addition, the experimental results also prove that the deployment of lightweight models can effectively reduce communication overhead in decentralized learning.

Key words: automatic modulation classification, decentralized learning, lightweight network, deep learning

CLC Number:

TP391

Jie YANG, Biao DONG, Xue FU, Yu WANG, Guan GUI. Lightweight decentralized learning-based automatic modulation classification method[J]. Journal on Communications, 2022, 43(7): 134-142.

Figures/Tables 16

References 20

[1]	化存卿 . 物联网安全检测与防护机制综述[J]. 上海交通大学学报, 2018,52(10): 1307-1313.
	HUA C Q . A survey of security detection and protection for Internet of things[J]. Journal of Shanghai Jiao Tong University, 2018,52(10): 1307-1313.
[2]	POPOOLA S I , ANDE R , ADEBISI B ,et al. Federated deep learning for zero-day botnet attack detection in IoT-edge devices[J]. IEEE Internet of Things Journal, 2022,9(5): 3930-3944.
[3]	霍添财 . 物联网终端设备恶意软件检测研究与设计[D]. 西安:西安电子科技大学, 2021.
	HUO T C . Research and design of malware detection of terminal devices in IoT networks[D]. Xi’an:Xidian University, 2021.
[4]	彭安妮, 周威, 贾岩 ,等. 物联网操作系统安全研究综述[J]. 通信学报, 2018,39(3): 22-34.
	PENG A N , ZHOU W , JIA Y ,et al. Survey of the Internet of things operating system security[J]. Journal on Communications, 2018,39(3): 22-34.
[5]	STOYANOVA M , NIKOLOUDAKIS Y , PANAGIOTAKIS S ,et al. A survey on the Internet of things (IoT) forensics:challenges,approaches,and open issues[J]. IEEE Communications Surveys ＆ Tutorials, 2020,22(2): 1191-1221.
[6]	张玉清, 周威, 彭安妮 . 物联网安全综述[J]. 计算机研究与发展, 2017,54(10): 2130-2143.
	ZHANG Y Q , ZHOU W , PENG A N . Survey of Internet of things security[J]. Journal of Computer Research and Development, 2017,54(10): 2130-2143.
[7]	梁浩然, 伍军, 赵程程 ,等. 基于博弈优化边缘学习的物联网入侵检测研究[J]. 物联网学报, 2021,5(2): 37-47.
	LIANG H R , WU J , ZHAO C C ,et al. Leveraging edge learning and game theory for intrusion detection in Internet of things[J]. Chinese Journal on Internet of Things, 2021,5(2): 37-47.
[8]	林冲, 闫文君, 张立民 ,等. 通信信号调制识别综述[J]. 中国电子科学研究院学报, 2021,16(11): 1074-1085.
	LIN C , YAN W J , ZHANG L M ,et al. An overview of communication signals modulation recognition[J]. Journal of China Academy of Electronics and Information Technology, 2021,16(11): 1074-1085.
[9]	代翱, 张海剑, 孙洪 . 联合时域和时频域特征的数字调制信号自动分类[J]. 信号处理, 2016,32(11): 1283-1292.
	DAI A , ZHANG H J , SUN H . Digital modulations automatic classification using the combination of several features extracted from time and time-frequence domain[J]. Journal of Signal Processing, 2016,32(11): 1283-1292.
[10]	向建, 高勇 . 基于GRU-CNN并联神经网络的自动调制识别[J]. 电讯技术, 2021,61(11): 1339-1343.
	XIANG J , GAO Y . Automatic modulation recognition based on GRU-CNN parallel neural network[J]. Telecommunication Engineering, 2021,61(11): 1339-1343.
[11]	桂冠, 王禹, 黄浩 . 基于深度学习的物理层无线通信技术:机遇与挑战[J]. 通信学报, 2019,40(2): 19-23.
	GUI G , WANG Y , HUANG H . Deep learning based physical layer wireless communication techniques:opportunities and challenges[J]. Journal on Communications, 2019,40(2): 19-23.
[12]	XU J L , LUO C B , PARR G ,et al. A spatiotemporal multi-channel learning framework for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2020,9(10): 1629-1632.
[13]	ZHANG Z F , LUO H , WANG C ,et al. Automatic modulation classification using CNN-LSTM based dual-stream structure[J]. IEEE Transactions on Vehicular Technology, 2020,69(11): 13521-13531.
[14]	ZHANG F X , LUO C B , XU J L ,et al. An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation[J]. IEEE Communications Letters, 2021,25(10): 3287-3290.
[15]	HUYNH-THE T , HUA C H , PHAM Q V ,et al. MCNet:an efficient CNN architecture for robust automatic modulation classification[J]. IEEE Communications Letters, 2020,24(4): 811-815.
[16]	张立志, 冉浙江, 赖志权 ,等. 分布式深度学习通信架构的性能分析[J]. 计算机工程与科学, 2021,43(3): 416-425.
	ZHANG L Z , RAN Z J , LAI Z Q ,et al. Performance analysis of distributed deep learning communication architecture[J]. Computer Engineering ＆ Science, 2021,43(3): 416-425.
[17]	刘艺璇, 陈红, 刘宇涵 ,等. 联邦学习中的隐私保护技术[J]. 软件学报, 2022,33(3): 1057-1092.
	LIU Y X , CHEN H , LIU Y H ,et al. Privacy-preserving techniques in federated learning[J]. Journal of Software, 2022,33(3): 1057-1092.
[18]	陈世达, 刘强, 韩亮 . 降低分布式训练通信的梯度稀疏压缩方法[J]. 浙江大学学报(工学版), 2021,55(2): 386-394.
	CHEN S D , LIU Q , HAN L . Gradient sparsification compression approach to reducing communication in distributed training[J]. Journal of Zhejiang University (Engineering Science), 2021,55(2): 386-394.
[19]	赵羽, 杨洁, 刘淼 ,等. 面向视频监控基于联邦学习的智能边缘计算技术[J]. 通信学报, 2020,41(10): 109-115.
	ZHAO Y , YANG J , LIU M ,et al. Federated learning based intelligent edge computing technique for video surveillance[J]. Journal on Communications, 2020,41(10): 109-115.
[20]	WANG Y , GUO L , ZHAO Y ,et al. Distributed learning for automatic modulation classification in edge devices[J]. IEEE Wireless Communications Letters, 2020,9(12): 2177-2181.

Metrics

Recommended 0

No Suggested Reading articles found!

超参数	值
训练周期/Epoch	500
学习率	0.001
优化器	Adma
批处理规模	400
边缘设备数/个	10

K ^G_S	FLOPS	参数量/个	模型权重/KB	分类性能
1×1	15.476×10³	91 046	485	57.46%
3×3	20.596×10³	111 046	565	62.84%
5×5	30.836×10³	151 046	725	62.27%
7×7	46.196×10³	211 046	965	62.77%

U	FLOPS	参数量/个	模型权重/KB	分类性能
32	20.474×10³	48 934	316	57.08%
64	20.502×10³	63 494	375	55.82%
128	20.596×10³	111 046	565	62.84%
256	20.931×10³	279 878	1228.8	62.66%

网络	FLOPS	参数量/个	模型权重/MB	分类性能
CNN	42.664×10³	2 190 283	8.793	52.17%
MCLDNN	36.322×10³	406 199	1.669	61.82%
CNN-LSTM	38.966×10³	340 939	1.396	61.93%
MCMBNN	20.596×10³	111 046	0.552	62.84%

网络	FLOPS	参数量/个	模型权重/KB	分类性能
V₁	20.596×10³	110 789	527	62.12%
V₂	21.087×10³	112 966	571	62.83%
V₃	32.129×10³	133 596	647	62.54%
V₄	20.642×10³	134 086	657	62.33%
MCMBNN	20.596×10³	111 046	565	62.84%

Lightweight decentralized learning-based automatic modulation classification method

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 20

Related Articles 15

Metrics

Recommended 0

[1]	Dongyu CHEN, Hua CHEN, Limin FAN, Yifang FU, Jian WANG. Research on test strategy for randomness based on deep learning [J]. Journal on Communications, 2023, 44(6): 23-33.
[2]	Rongpeng LI, Bingyan WANG, Honggang ZHANG, Zhifeng ZHAO. Design of knowledge enhanced semantic communication receiver [J]. Journal on Communications, 2023, 44(6): 70-76.
[3]	Shuai MA, Ke PEI, Huayan QI, Hang LI, Wen CAO, Hongmei WANG, Hailiang XIONG, Shiyin LI. Research on geomagnetic indoor high-precision positioning algorithm based on generative model [J]. Journal on Communications, 2023, 44(6): 211-222.
[4]	Xiuzhang YANG, Guojun PENG, Zichuan LI, Yangqi LYU, Side LIU, Chenguang LI. Research on entity recognition and alignment of APT attack based on Bert and BiLSTM-CRF [J]. Journal on Communications, 2022, 43(6): 58-70.
[5]	Yong LIAO, Shiyi WANG. CSI feedback algorithm based on RM-Net for massive MIMO systems in high-speed mobile environment [J]. Journal on Communications, 2022, 43(5): 166-176.
[6]	Yurong LIAO, Haining WANG, Cunbao LIN, Yang LI, Yuqiang FANG, Shuyan NI. Research progress of deep learning-based object detection of optical remote sensing image [J]. Journal on Communications, 2022, 43(5): 190-203.
[7]	Zenghua ZHAO, Yuefan TONG, Jiayang CUI. Device-independent Wi-Fi fingerprinting indoor localization model based on domain adaptation [J]. Journal on Communications, 2022, 43(4): 143-153.
[8]	Yong LIAO, Gang CHENG, Yujie LI. CSI feedback algorithm based on deep unfolding for massive MIMO systems [J]. Journal on Communications, 2022, 43(12): 77-88.
[9]	Xueyuan DUAN, Yu FU, Kun WANG, Bin LI. LDoS attack detection method based on simple statistical features [J]. Journal on Communications, 2022, 43(11): 53-64.
[10]	Junyan HUO, Ruipeng QIU, Yanzhuo MA, Fuzheng YANG. Reference frame list optimization algorithm in video coding by quality enhancement of the nearest picture [J]. Journal on Communications, 2022, 43(11): 136-147.
[11]	Haiyan KANG, Yuanrui JI. Research on federated learning approach based on local differential privacy [J]. Journal on Communications, 2022, 43(10): 94-105.
[12]	Hongxia ZHANG, Qi WANG, Dengyue WANG, Ben WANG. Honeypot contract detection of blockchain based on deep learning [J]. Journal on Communications, 2022, 43(1): 194-202.
[13]	Yan YAN, Yiming CONG, Mahmood Adnan, Quanzheng SHENG. Statistics release and privacy protection method of location big data based on deep learning [J]. Journal on Communications, 2022, 43(1): 203-216.
[14]	Ye ZHU, Yilin YU, Yingchun GUO. HRDA-Net: image multiple manipulation detection and location algorithm in real scene [J]. Journal on Communications, 2022, 43(1): 217-226.
[15]	Xiaoyuan YANG, Xinliang BI, Jia LIU, Siyuan HUANG. High-capacity image steganography algorithm combining image encryption and deep learning [J]. Journal on Communications, 2021, 42(9): 96-105.