Multimodal Modulation Recognition Method Based on BLR Parallel Structure

NAVIGATE

Table of Contents

STATISTICS

Viewed16

Downloads41

Multimodal Modulation Recognition Method Based on BLR Parallel Structure

[HTML] PDF下载 (41)

[1]JIANG Hua,XIAO Kejie,HU Po,et al.Multimodal Modulation Recognition Method Based on BLR Parallel Structure[J].Journal of Zhengzhou University (Engineering Science),2026,47(3):76-82,116.[doi:10.13705/j.issn.1671-6833.2025.03.019]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 47 Number of periods: 2026 Issue 3 Page number: 76-82,116 Column: Public date: 2026-05-27

Title:: Multimodal Modulation Recognition Method Based on BLR Parallel Structure

Author(s):: JIANG Hua, XIAO Kejie, HU Po, GONG Kexian, ZHAO Zhenyu; School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China

Keywords:: automatic modulation recognition; convolutional neural network; multimodal; feature fusion; parallel structure

CLC:: TN911.7

DOI:: 10.13705/j.issn.1671-6833.2025.03.019

Abstract:: Aiming at the problem that existing convolutional neural network (CNN)-based modulation recognition methods are highly dependent on single modal data (e.g., IQ sequences) and difficult to adequately extract multidimensional features of signals, in this study a multimodal parallel structural modulation recognition method was proposed based on bidirectional long short-term memory network (BiLSTM) and residual network (ResNet), termed the BiLSTM-ResNet (BLR network). Firstly, the temporal features of IQ data were extracted by BiLSTM in the upper branch, and the spatial features of constellation maps were extracted by ResNet-18 in the lower branch. Secondly, serial feature fusion was used in the decision fusion module to better exploit the complementary nature of the multimodal data. Lastly, the signal modulation styles were recognised with the help of the model’s feature extraction capability. In this study, experimental validation was carried out on the publicly available dataset RML2018.01a. The experimental results showed that the overall recognition accuracy of BLR network in the 6-30 dB SNR interval was stable at 96.48%, 2.61% and 3.91% higher than that of the single-modal ResNet and BiLSTM models, respectively, and 1.25% higher than that of the CNN-LSTM model with concatenated structure, which verified that the model proposed in this paper had the modulation recognition problem Effectiveness.

References:: [1]WEI W, MENDEL J M. Maximum-likelihood classification for digital amplitude-phase modulations[J]. IEEE Transactions on Communications, 2000, 48(2): 189-193.
[2]张承畅, 余洒, 徐余, 等. 人工神经网络在调制识别中的应用综述[J]. 重庆邮电大学学报(自然科学版), 2022, 34(2): 181-192.
ZHANG C C, YU S, XU Y, et al. Survey of artificial neural network applied to modulation recognition[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2022, 34(2): 181-192.
[3]HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[4]POSTADJIAN T, LE BRIS A, MALLET C, et al. Superpixel partitioning of very high resolution satellite images for large-scale classification perspectives with deep convolutional neural networks[C]∥IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2018: 1328-1331.
[5]周鑫, 何晓新, 郑昌文. 基于图像深度学习的无线电信号识别[J]. 通信学报, 2019, 40(7): 114-125.
ZHOU X, HE X X, ZHENG C W. Radio signal recognition based on image deep learning[J]. Journal on Communications, 2019, 40(7): 114-125.
[6]CHUNG J S, SENIOR A, VINYALS O, et al. Lip reading sentences in the wild[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 3444-3453.
[7]O’SHEA T J, CORGAN J, CLANCY T C. Convolutional radio modulation recognition networks[M]∥Engineering Applications of Neural Networks. Cham: Springer International Publishing, 2016: 213-226.
[8]WU Y L, LI X J, FANG J. A deep learning approach for modulation recognition via exploiting temporal correlations[C]∥2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Piscataway: IEEE, 2018: 1-5.
[9]WANG Y, LIU M, YANG J, et al. Data-driven deep learning for automatic modulation recognition in cognitive radios[J]. IEEE Transactions on Vehicular Technology, 2019, 68(4): 4074-4077.
[10]王晓明, 许梦竹. 基于深度学习的调制识别方法研究[J]. 中国无线电, 2023(5): 47-51.
WANG X M, XU M Z. Radio signal modulation recognition method based on deep learning[J]. China Radio, 2023(5): 47-51.
[11]章昕亮, 李天昀, 龚佩, 等. 联合深度学习和专家先验特征的信号调制识别[J]. 信息工程大学学报, 2023, 24(2): 129-134.
ZHANG X L, LI T Y, GONG P, et al. Signal modulation recognition based on joint deep learning and expert prior features[J]. Journal of Information Engineering University, 2023, 24(2): 129-134.
[12]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.
ZHA X, PENG H, QIN X, et al. Modulation recognition method based on multi-inputs convolution neural network[J]. Journal on Communications, 2019, 40(11): 30-37.
[13]任彦洁, 唐晓刚, 张斌权, 等. 基于时间卷积网络的通信信号调制识别算法[J]. 无线电工程, 2023, 53(4): 807-814.
REN Y J,TANG X G, ZHANG B Q, et al. Communication signal modulation recognition algorithm based on a temporal convolutional network [J]. Radio Engineering, 2023, 53(4): 807-814.
[14]WEST N E, O’SHEA T. Deep architectures for modulation recognition[C]∥2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). Piscataway: IEEE, 2017: 1-6.
[15]翁建新, 赵知劲, 占锦敏. 利用并联CNN-LSTM的调制样式识别算法[J]. 信号处理, 2019, 35(5): 870-876.
WENG J X, ZHAO Z J, ZHAN J M. Modulation recognition algorithm by using parallel CNN-LSTM[J]. Journal of Signal Processing, 2019, 35(5): 870-876.
[16] SNOAP J A, POPESCU D C, SPOONER C M. On deep learning classification of digitally modulated signals using raw I/Q data[C]∥2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC). Piscataway: IEEE, 2022: 441-444.
[17]张富强, 曾夏, 白筠妍, 等. 多模态数据融合的加工作业动态手势识别方法[J]. 郑州大学学报(工学版), 2024, 45(5): 30-36.
ZHANG F Q, ZENG X, BAI J Y, et al. Dynamic gesture recognition method for machining operations based on multi-modal data fusion[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(5): 30-36.
[18] QI P H, ZHOU X Y, ZHENG S L, et al. Automatic modulation classification based on deep residual networks with multimodal information[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(1): 21-33.
[19]张茜茜, 王禹, 林云, 等. 基于深度学习的自动调制识别方法综述[J]. 无线电通信技术, 2022, 48(4): 697-710.
ZHANG X X, WANG Y, LIN Y, et al. A comprehensive survey of deep learning-based automatic modulation recognition methods[J]. Radio Communications Technology, 2022, 48(4): 697-710.
[20] BAI S J, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. (2018-04-19)[2025-0827]. https:∥arxiv.org/abs/1803.01271.
[21] YU L, CHEN J, DING G R, et al. Spectrum prediction based on taguchi method in deep learning with long shortterm memory[J]. IEEE Access, 2018, 6: 45923-45933.
[22] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 770-778.
[23]黄杰, 张顺生, 陈爽. 基于深度学习网络融合的自动调制分类方法[J]. 信号处理, 2023, 39(1): 42-50.
HUANG J, ZHANG S S, CHEN S. Automatic modulation classification method based on deep learning network fusion[J]. Journal of Signal Processing, 2023, 39(1): 42-50.
[24]邓远征, 白立云. 基于时空联合与注意力机制的调制识别研究与实现[J]. 无线电工程, 2024, 54(12): 2913-2922.
DENG Y Z,BAI L Y. Research and implementation of modulation recognition based on spatiotemporal joint and attention mechanism [J]. Radio Engineering, 2024, 54(12): 2913-2922.[25] O’SHEA T J, ROY T, CLANCY T C. Over-the-air deep learning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1): 168-179.

Similar References:

Memo

Last Update: 2026-05-27