[1]高洪元,王世豪,程建华,等.冲击噪声下基于演化长短时记忆神经网络的调制信号识别[J].智能系统学报,2023,18(4):676-687.[doi:10.11992/tis.202205002]
GAO Hongyuan,WANG Shihao,CHENG Jianhua,et al.Modulation signal recognition based on evolutionary long short-term memory neural network under impulse noise[J].CAAI Transactions on Intelligent Systems,2023,18(4):676-687.[doi:10.11992/tis.202205002]
点击复制
GAO Hongyuan,WANG Shihao,CHENG Jianhua,et al.Modulation signal recognition based on evolutionary long short-term memory neural network under impulse noise[J].CAAI Transactions on Intelligent Systems,2023,18(4):676-687.[doi:10.11992/tis.202205002]
冲击噪声下基于演化长短时记忆神经网络的调制信号识别
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第4期
页码:
676-687
栏目:
学术论文—机器学习
出版日期:
2023-07-15
- Title:
- Modulation signal recognition based on evolutionary long short-term memory neural network under impulse noise
- Keywords:
- modulating signal recognition; impulsive noise; convolution neural network (CNN); quantum sailfish optimization algorithm (QSFA); long short-term memory (LSTM) neural network; stable distribution; hyper parameters; short time Fourier transform
- 分类号:
- TP183; TN911.7
- 摘要:
- 为了解决冲击噪声下长短时记忆(long short term memory，LSTM)神经网络调制信号识别方法抗冲击噪声能力弱和超参数难以确定的问题，本文提出了一种演化长短时记忆神经网络的调制识别方法。利用基于短时傅里叶变换的卷积神经网络(convolution neural network，CNN)去噪模型对数据集去噪；结合量子计算机制和旗鱼优化器(sailfish optimizer, SFO)设计了量子旗鱼算法(quantum sailfish algorithm, QSFA)去演化LSTM神经网络以获得最优的超参数；使用演化长短时记忆神经网络作为分类器进行自动调制信号识别。仿真结果表明，采用所设计的CNN去噪和演化长短时记忆神经网络模型，识别准确率有了大幅度的提高。量子旗鱼算法演化LSTM神经网络模型降低了传统LSTM神经网络容易陷于局部极小值或者过拟合的概率，当混合信噪比为0 dB，所提方法对11种调制信号的平均识别准确率达到90%以上。
- Abstract:
- In order to solve the problems of weak resistance against impulsve noise and difficulty in determining hyperparameters of the modulation signal recognition method with long short-term memory (LSTM) neural network under impulse noise, this paper presents a modulation recognition method based on evolutionary LSTM neural network. The convolution neural network (CNN) denoising model based on short-time Fourier transform is used to denoise the data set. Then, combined with the quantum computation mechanism and sailfish optimizer (SFO), the quantum sailfish algorithm (QSFA) is designed to evolve LSTM neural network to obtain the optimal hyper-parameters. An evolutionary LSTM neural network is used as a classifier for automatic modulating signal recognition. Simulation results show that the recognition accuracy is greatly improved by using the designed CNN denoising and evolutionary LSTM neural network model. Moreover, the evolutionary LSTM neural network model based on quantum sailfish algorithm reduces the probability that traditional LSTM neural network is easy to fall into local minimum or over fitting. When the mixed signal-to-noise ratio (MSNR) is 0 dB, the average recognition accuracy of the proposed method for 11 modulated signals is more than 90%.
- 参考文献/References:
-
[1] IGLESIAS V, GRAJAL J, YESTE-OJEDA O. Automatic modulation classifier for military applications[C]//2011 19th European Signal Processing Conference. Barcelona: IEEE, 2011: 1814?1818.
[2] DOBRE O A, ABDI A, BAR-NESS Y, et al. Survey of automatic modulation classification techniques: classical approaches and new trends[J]. IET communications, 2007, 1(2): 137–156.
[3] 刘明骞, 李兵兵, 曹超凤, 等. 认知无线电中非高斯噪声下数字调制信号识别方法[J]. 通信学报, 2014, 35(1): 82–88
LIU Mingqian, LI Bingbing, CAO Chaofeng, et al. Recognition method of digital modulation signal under non Gaussian noise in cognitive radio[J]. Journal on communications, 2014, 35(1): 82–88
[4] AALO V A, PEPPAS K P, EFTHYMOGLOU G, et al. Evaluation of average bit error rate for wireless networks with alpha-stable interference[J]. Electronics letters, 2014, 50(1): 47–49.
[5] TIAN Xiaodi, SUN Xiaodong, YU Xiaohui, et al. Modulation pattern recognition of communication signals based on fractional low-order choi-williams distribution and convolutional neural network in impulsive noise environment[C]//2019 IEEE 19th International Conference on Communication Technology. Xi’an: IEEE, 2019: 188-192.
[6] TSIHRINTZIS G A, NIKIAS C L. Fast estimation of the parameters of alpha-stable impulsive interference[J]. IEEE transactions on signal processing, 1996, 44(6): 1492–1503.
[7] 查雄, 彭华, 秦鑫, 等. 基于多端卷积神经网络的调制识别方法[J]. 通信学报, 2019, 40(11): 30–37
CHA Xiong, PENG Hua, QIN Xin, et al. Modulation recognition method based on multi-inputs convolution neural network[J]. Journal on communications, 2019, 40(11): 30–37
[8] WANG Yu, LIU Miao, YANG Jie, et al. Data-driven deep learning for automatic modulation recognition in cognitive radios[J]. IEEE transactions on vehicular technology, 2019, 68(4): 4074–4077.
[9] MENG Fan, CHEN Peng, WU Lenan, et al. Automatic modulation classification: a deep learning enabled approach[J]. IEEE transactions on vehicular technology, 2018, 67(11): 10760–10772.
[10] C?MARA T V R O, LIMA A D L, LIMA B M M, et al. Automatic modulation classification architectures based on cyclostationary features in impulsive environments[J]. IEEE access, 2019, 7: 138512–138527.
[11] GAO H Y, WANG S H, SU Y M, et al. Evolutionary neural network based on quantum elephant herding algorithm for modulation recognition in impulse noise[J]. KSII transactions on Internet and information systems, 2021, 15(7): 2356–2376.
[12] ZHANG Kun, LIANG Lin, HUANG Ying, et al. A network traffic prediction model based on quantum inspired PSO and neural network[C]//2013 Sixth International Symposium on Computational Intelligence and Design. Hangzhou: IEEE, 2013: 219-222.
[13] DENG Wu, LIU Hailong, XU Junjie, et al. An improved quantum-inspired differential evolution algorithm for deep belief network[J]. IEEE transactions on instrumentation and measurement, 2020, 69(10): 7319-7327.
[14] 杨发权, 李赞, 罗中良. 混合调制信号调制识别方法[J]. 中山大学学报(自然科学版), 2014, 53(1): 42–46
YANG Faquan, LI Zan, LUO Zhongliang. Method of modulation recognition of mixed modulation signal[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2014, 53(1): 42–46
[15] 刘高辉, 张娟娟. α稳定分布噪声下数字频移键控信号的分数低阶循环谱分析[J]. 电波科学学报, 2017, 32(1): 65–72
LIU Gaohui, ZHANG Juanjuan. Fractional lower order cyclic spectrum analysis of digital frequency shift keying signals under the alpha stable distribution noise[J]. Chinese journal of radio science, 2017, 32(1): 65–72
[16] KOUNOVSKY T, MALEK J. Single channel speech enhancement using convolutional neural network[C]// IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics. Donostia: IEEE, 2017: 1?5.
[17] 李悦, 马晓川, 王磊, 等. 非高斯环境下的深度学习脉冲信号去噪与重构[J]. 应用声学, 2021, 40(1): 131–141
LI Yue, MA Xiaochuan, WANG Lei, et al. Using deep learning to de-noise and reconstruct pulse signals in non-Gaussian environment[J]. Journal of applied acoustics, 2021, 40(1): 131–141
[18] SHADRAVAN S, NAJI H R, BARDSIRI V K. The sailfish optimizer: a novel nature-inspired metaheuristic algorithm for solving constrained engineering optimization problems[J]. Engineering applications of artificial intelligence, 2019, 80: 20-34.
[19] 高洪元, 刁鸣. 量子群智能及其在通信技术中的应用[M]. 北京: 电子工业出版社, 2016: 1?3.
[20] SHAO Bilin, LI Maolin, ZHAO Yu, et al. Nickel price forecast based on the LSTM neural network optimized by the improved PSO algorithm[J]. Mathematical problems in engineering, 2019, 2019: 1–15.
[21] KALLURI S, ARCE G R. Adaptive weighted myriad filter algorithms for robust signal processing in/spl alpha /-stable noise environments[J]. IEEE transactions on signal processing, 1998, 46(2): 322–334.
[22] MENG Xianbing, GAO X Z, LU Lihua, et al. A new bio-inspired optimisation algorithm: bird swarm algorithm[J]. Journal of experimental & theoretical artificial intelligence, 2016, 28(4): 673–687.
[23] SEO J H, IM C H, HEO C G, et al. Multimodal function optimization based on particle swarm optimization[J]. IEEE transactions on magnetics, 2006, 42(4): 1095–1098.
[24] DHIMAN G, KUMAR V. Seagull optimization algorithm: theory and its applications for large-scale industrial engineering problems[J]. Knowledge-based systems, 2019, 165: 169–196.
[25] WANG Gaige, DEB S, COELHO L. Elephant herding optimization[C]//2015 3rd International Symposium on Computational and Business Intelligence . Bali: IEEE, 2015: 1-5.
[26] HU Yaohua, LIU Mingqian, CAO Chaofeng, et al. Modulation classification in Alpha stable noise[C]//2016 IEEE 13th International Conference on Signal Processing. Chengdu: IEEE, 2016: 1275-1278.
[27] 杨洁, 弋佳东. 改进GA优化BP神经网络的雷达信号识别[J]. 西安邮电大学学报, 2019, 24(6): 11–15
YANG Jie, YI Jiadong. Radar signal recognition based on BP neural network optimized by improved GA[J]. Journal of Xi’an University of Posts and Telecommunications, 2019, 24(6): 11–15
[28] XIE Wenwu, HU Sheng, YU Chao, et al. Deep learning in digital modulation recognition using high order cumulants[J]. IEEE access, 2019, 7: 63760–63766.
[29] JIANG Xinrui, CHEN Hui, ZHAO Yaodong, et al. Automatic modulation recognition based on mixed-type features[J]. International journal of electronics, 2021, 108(1): 105–114.
备注/Memo
收稿日期:2022-05-06。
基金项目:国家自然科学基金项目（62073093）；黑龙江省自然科学基金项目（LH2020F017）；黑龙江省博士后科研启动金项目（LBH-Q19098）.
作者简介:高洪元，副教授，博士生导师，主要研究方向为无线能量采集通信、智能计算、人工智能、无线电信号识别和分类、阵列信号处理、认知无线电、5G中的HetNets、通信理论、图像处理和massive MIMO。主持国家自然科学基金项目、中国博士后科学基金特别资助等20余项，授权发明专利110项。发表学术论文100余篇，出版学术专著2部。;王世豪，硕士研究生，主要研究方向为智能计算、机器学习、调制信号识别和无人机集群信息交互。;程建华，教授，主要研究方向为惯性导航系统、卫星导航和综合导航。主持国家自然科学基金项目、军事“973”项目、装备预研项目等20余项，获省部级科技奖项7项，授权发明专利13项。发表学术论文100余篇，出版学术著作7部。
通讯作者:高洪元.E-mail:gaohongyuan@hrbeu,edu.cn
更新日期/Last Update:
1900-01-01