[1]夏兆宇,林玉洁,胡春源,等.基于多准则融合与智能决策的调制识别算法[J].郑州大学学报(工学版),2024,45(pre):2.[doi:10.13705/j.issn.1671-6833.2024.04.015]
 XIA Zhaoyu,LIN Yujie,HU Chunyuan,et al.Modulation Recognition Algorithm Based on Multi-Criteria Fusion and Intelligent Decision[J].Journal of Zhengzhou University (Engineering Science),2024,45(pre):2.[doi:10.13705/j.issn.1671-6833.2024.04.015]
点击复制

基于多准则融合与智能决策的调制识别算法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
45
期数:
2024年pre
页码:
2
栏目:
出版日期:
2024-11-30

文章信息/Info

Title:
Modulation Recognition Algorithm Based on Multi-Criteria Fusion and Intelligent Decision
作者:
夏兆宇林玉洁胡春源吴梓豪
(北京理工大学 信息与电子学院,北京 1 00081)
Author(s):
XIA Zhaoyu LIN Yujie HU Chunyuan WU Zihao
(School of Information and Electronics, Beijing Institute of Technology, Beijing 100081 , China)
关键词:
调制识别高阶累积延伸量CART决策树基尼系数多准则融合剪枝算法
Keywords:
modulation recognition higher-order cumulative extension CART decision tree Gini coefficient multi-criteria fusion pruning algorithm
分类号:
TN98, TN929.5
DOI:
10.13705/j.issn.1671-6833.2024.04.015
文献标志码:
A
摘要:
针对6G通信信号调制识别阶数要求高、低信噪比环境调制识别难的问题,结合人工智能技术与现代信号处理技术,提出一种基于多准则融合与智能决策的调制识别算法。该算法分为多准则融合网络与智能决策网络两部分。多准则融合网络计算标准调制信号的高阶累积延伸量,采用局部最优解方式遍历所有潜在门限,以基尼系数和确定度增熵确定判决门限。智能决策网络采用CART型架构,以判决门限为标准对未知信号的调制体制进行识别,并使用剪枝算法对模型迭代优化,最终得到最优决策树,形成基于多准则融合与智能决策的调制识别算法。实验结果表明,在0dB信噪比情况下,算法能够对16QAM、64QAM、128QAM、1024QAM、2PSK、4PSK、8PSK、2FSK、4FSK进行精准识别,综合识别率达到99.4%。与其他方法对比,调制体制综合识别率、可识别调制体制种类均有提升。
Abstract:
Aiming at the requirement of high modulation order identification and the difficulty of modulation identification in low signal-to-noise ratio environment in 6G communication, a modulation recognition algorithm based on multi-criteria fusion and intelligent decision was proposed by combining artificial intelligence technology and modern signal processing technology. The algorithm was divided into two parts: multi-criteria fusion network and intelligent decision network. The multi-criteria fusion network calculated the higher-order cumulative extensions of the standard modulation signals, traversed all the potential thresholds by using local optimal solutions, and determined the judgment thresholds by Gini coefficient and the entropy of certainty gain. The intelligent decision network adopted a CART architecture to recognize the modulation format of unknown signals using the determined judgment thresholds, and the model was iterative optimized using a pruning algorithm to obtain the finally optimal decision tree, forming a modulation recognition algorithm based on multi-criteria fusion and intelligent decision making. Experimental results showed that the algorithm could accurately recognize 16QAM, 64QAM, 128QAM, 1024QAM, 2PSK, 4PSK, 8PSK, 2FSK, 4FSK at 0dB SNR, and the comprehensive recognition accuracy reached 99.4%. Compared with other methods, the modulation recognition accuracy and the types of recognizable modulation have been improved

参考文献/References:

[1].AN Z L, ZHANG T Q, SHEN M, et al. Series-Constellation feature based blind modulation recognition for beyond 5G MIMO-OFDM systems with channel fading [J]. IEEE Transactions on Cognitive Communications and Networking, 2022, 8(2): 793-811.
[2].JANNAH R R, KHAYAM U. Design, implementation, and testing of partial discharge signal pattern recognition and judgment system application using statistical method [J]. Proceedings of the Joint International Conference on Electric Vehicular Technology and Industrial, Mechanical, Electrical and Chemical Engineering, 2015: 314-318.
[3].LIU Y B, LIU Y, YANG C. Modulation recognition with graph convolution network [J]. IEEE Wireless Communications Letters, 2019, 26(7): 624-627.
[4].ZHANG X L, LI T Y, GONG P, et al. Open set recognition of communication signal modulation based on deep learning [J]. IEEE Communications Letters, 2022, 26(7): 1588-1592.
[5].ZHANG W, SUN Y, XUE K, et al. Research on modulation recognition algorithm based on channel and spatial self-attention mechanism [J]. IEEE Access, 2023 11: 68617-68631.
[6].DENG W, WANG X, HUANG, Z T, et al. Modulation classifier: a few-shot learning sem i-supervised method based on multimodal information and domain adversarial network [J]. IEEE Communications Letters, 2023, 27(2): 576-580.
[7].WANG T, HOU T H, ZHANG H Y, et al. Deep learning based modulation recognition with multi-cue fusion [J]. IEEE Wireless Communications Letters, 2021, 10(8): 1757-1760.
[8].LIN S G, ZENG Y, GONG Y. Modulation recognition using signal enhancement and multistage attention mechanism [J]. IEEE Transactions on Wireless Communications, 2022, 21(11): 9921-9935.
[9].YANG C, HE Z M, PENG Y, et al. Deep learning aided method for automatic modulation recognition [J]. IEEE Access, 2019 10: 1-6.
[10].ZHAO X D, ZHOU X H, XIONG , et al. Automatic modulation recognition based on multi-dimensional feature extraction [C]// The 12th International Conference on Wireless Communications and Signal Processing. Nanjing, China,: 2020. 823-828.
[11].JI M R, HUANG C Z, LUO R S. Automatic modulation recognition based on spatio-temporal features fusion[C]// IEEE 12th International Conference on Electronics Information and Emergency Communication (ICEIEC). Beijing, China. 2022. 89-93.
[12].HE Z W. Communication signal modulation recognition based on time-frequency domain analysis and Bayesian optimized decision tree algorithm [C]//IEEE International Conference on Data Science and Computer Application (ICDSCA). Dalian, China: 2021. 69-73.
[13].XU S, LIU L T, ZHAO Z K. DTFTC-Net: radar modulation recognition with deep time-frequency transformation [J]. IEEE Transactions on Cognitive Communications and Networking, 2023, 9(5): 1200-1210.
[14].HOU C B, LIU G W, TIAN Q, et al. Multi-signal modulation classification using sliding window detection and complex convolution network in frequency domain [J]. IEEE Internet of Things Journal, 2022, 9(19): 19438-19449.
[15].ZHANG Q W, XU Z, ZHANG P Y. Modulation recognition using wavelet transform based on Alex-Net [C]//2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT). Dalian, China. 2019 : 339- 342.
[16].YAO R G, WANG P, ZUO X Y, et al. Intelligent modulation pattern recognition based on wavelet approximate coefficient Entropy in Cognitive Radio Networks [J]. IEEE Access, 2020, 8: 226176-226187.
[17].ZENG Y, ZHANG M, HAN F, et al. Spectrum Analysis and convolution neural network for automatic modulation recognition [J]. IEEE Wireless Communications Letters, 2019, 8(3): 929-932.
[18].张贤达. 现代信号处理第三版[M].清华大学出版社,2015.
[ZHANG X D. Modern signal processing(third edition) [M]. Tsinghua University Press, 2015.
[19].ZENG L, CHIANG H D, LIANG D, et al. Trust-Tech source-point method for systematically computing multiple local optimal solutions: theory and method [J]. IEEE Transactions on Cybernetics, 2022, 52(11): 11686-11697.
[20].ZHAO Z, YANG A Y, GUO P. A modulation format identification method based on information entropy analysis of received optical communication signal [J]. IEEE Access, 2019, 7: 41492-41497.
[21].韩刚涛, 马瑞鹏, 吴迪.基于时频图切割的宽带信号智能检测与识别[J].郑州大学学报(工学版), 2023, 44(5):42-49.
HAN D T, MA R P, WU D. Intelligent detection and identification of broadband signals based on time-frequency map cutting [J]. Journal of Zhengzhou University (Engineering Science), 2023, 44(5): 42-49.
[22].LAI C M, KUO T J. Available capacity computation model based on long short-term memory recurrent neural network for gelled-electrolyte batteries in golf carts [J]. IEEE Access, 2022, 10: 54433-54444.
[23].李航. 统计学习方法第二版[M].清华大学出版社,2019.
LI H. Statistical learning algorithm (second edition) [M]. Tsinghua University Press, 2019.

备注/Memo

备注/Memo:
收稿日期:2024-03-01;修订日期:2024-04-10基金项目:国家重点研发计划资助(2023YFF0717400);国家自然科学基金项目(62001030)通信作者:林玉洁(1989—),女,山东威海人,北京理工大学实验师,博士,主要从事无线通信研究,E-mail:linyujie@bit.edu.cn
更新日期/Last Update: 2024-10-10