A Survey of Applications of Deep Learning in Radio Signal Modulation Recognition
Source abstract
Abstract
With the continuous development of communication technology, the wireless communication environment becomes more and more complex with various intentional and unintentional signals. Radio signals are modulated in different ways. The traditional radio modulation recognition technology cannot recognize the modulation modes accurately. Consequently, the communication system has embraced Deep Learning (DL) models as they can automatically recognize the modulation modes and have better accuracy. This paper systematically summarizes the related contents of radio Automatic Modulation Recognition (AMR) based on DL over the last seven years. First, we summarize the current research status of modulation recognition and the necessity of AMR research based on DL. Then, we review current radio AMR methods based on DL. In addition, we also propose a network model of AMR based on Convolutional Neural Network (CNN) and prove its effectiveness. Finally, we highlight existing challenges and research directions of radio AMR based on DL.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Wireless Signal Modulation Classification · Internet Traffic Analysis and Secure E-voting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Ocean Information Engineering, Jimei University, Xiamen 361021, China
School of Informatics, Xiamen University, Xiamen 361005, China
School of Electrical Engineering, Hebei University of Technology, Tianjin 300401, China
School of Advanced Manufacturing, Fuzhou University, Jinjiang 362251, China
References (100+)
Show source-provided references
1. Cognitive radio: Making software radios more personal10.1109/98.788210 ↗
2. Research on radar signal recognition based on automatic machine learning10.1007/s00521-019-04494-1 ↗
3. Zhu, Z., and Nandi, A.K. (2015). Automatic Modulation Classification: Principles, Algorithms and Applications, John Wiley & Sons.10.1002/9781118906507 ↗
4. Maximum-likelihood classification for digital amplitude-phase modulations10.1109/26.823550 ↗
5. On the likelihood-based approach to modulation classification10.1109/TWC.2009.12.080883 ↗
6. Hybrid maximum likelihood modulation classification for continuous phase modulations10.1109/LCOMM.2016.2517007 ↗
7. Survey of automatic modulation classification techniques: Classical approaches and new trends10.1049/iet-com:20050176 ↗
8. Automatic modulation classification using combination of genetic programming and KNN
9. Automatic intrapulse modulation classification of advanced LPI radar waveforms10.1109/TAES.2017.2667142 ↗
10. A Gabor atom network for signal classification with application in radar target recognition10.1109/78.969508 ↗
11. Automatic modulation classification based on kernel density estimation10.1109/CJECE.2016.2570250 ↗
12. Low-complexity cyclostationary-based modulation classifying algorithm10.1016/j.aeue.2017.02.008 ↗
13. Spectrum sensing and modulation classification for cognitive radios using cumulants based on fractional lower order statistics10.1016/j.aeue.2012.11.004 ↗
14. Nishani, E., and Çiço, B. (2017, January 11–15). Computer vision approaches based on deep learning and neural networks: Deep neural networks for video analysis of human pose estimation. Proceedings of the 2017 6th Mediterranean Conference on Embedded Computing (MECO), Bar, Montenegro.10.1109/MECO.2017.7977207 ↗
15. Wang, P. (2020, January 10–12). Research and design of smart home speech recognition system based on deep learning. Proceedings of the 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), Chongqing, China.10.1109/CVIDL51233.2020.00-98 ↗
16. Dong, Y.n., and Liang, G.s. (2019, January 8–10). Research and discussion on image recognition and classification algorithm based on deep learning. Proceedings of the 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Taiyuan, China.10.1109/MLBDBI48998.2019.00061 ↗
17. Zunjani, F.H., Sen, S., Shekhar, H., Powale, A., Godnaik, D., and Nandi, G. (2018, January 14–15). Intent-based object grasping by a robot using deep learning. Proceedings of the 2018 IEEE 8th International Advance Computing Conference (IACC), Greater Noida, India.10.1109/IADCC.2018.8692134 ↗
18. Kim, B., Kim, J., Chae, H., Yoon, D., and Choi, J.W. (2016, January 19–21). Deep neural network-based automatic modulation classification technique. Proceedings of the 2016 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Republic of Korea.10.1109/ICTC.2016.7763537 ↗
19. O’Shea, T.J., Corgan, J., and Clancy, T.C. (2016). Convolutional radio modulation recognition networks. Engineering Applications of Neural Networks. EANN 2016, Springer. Communications in Computer and Information Science.10.1007/978-3-319-44188-7_16 ↗
20. O’Shea, T.J., Hitefield, S., and Corgan, J. (2016, January 7–9). End-to-end radio traffic sequence recognition with recurrent neural networks. Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington, DC, USA.10.1109/GlobalSIP.2016.7905847 ↗
21. Mendis, G.J., Wei, J., and Madanayake, A. (2016, January 14–16). Deep learning-based automated modulation classification for cognitive radio. Proceedings of the 2016 IEEE International Conference on Communication Systems (ICCS), Shenzhen, China.10.1109/ICCS.2016.7833571 ↗
22. k-Sparse Autoencoder-Based Automatic Modulation Classification with Low Complexity10.1109/LCOMM.2017.2717821 ↗
23. Hong, D., Zhang, Z., and Xu, X. (2017, January 13–16). Automatic modulation classification using recurrent neural networks. Proceedings of the 2017 3rd IEEE International Conference on Computer and Communications (ICCC), Chengdu, China.10.1109/CompComm.2017.8322633 ↗
24. Deep learning models for wireless signal classification with distributed low-cost spectrum sensors10.1109/TCCN.2018.2835460 ↗
25. Ghanem, H.S., Al-Makhlasawy, R.M., El-Shafai, W., Elsabrouty, M., Hamed, H.F., Salama, G.M., and El-Samie, F.E.A. (2022). Wireless modulation classification based on Radon transform and convolutional neural networks. J. Ambient. Intell. Humaniz. Comput.10.1007/s12652-021-03650-7 ↗
26. Ghanem, H.S., Shoaib, M.R., El-Gazar, S., Emara, H., El-Shafai, W., El-Moneim, S.A., El-Fishawy, A.S., Taha, T.E., Hamed, H.F., and El-Banby, G.M. (2022). Automatic modulation classification with 2D transforms and convolutional neural network. Trans. Emerg. Telecommun. Technol., e4623.10.1002/ett.4623 ↗
27. An efficient modulation classification method using signal constellation diagrams with convolutional neural networks, Gabor filtering and thresholding10.1002/ett.4459 ↗
28. Hamidi-Rad, S., and Jain, S. (2021, January 7–11). Mcformer: A transformer based deep neural network for automatic modulation classification. Proceedings of the 2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain.10.1109/GLOBECOM46510.2021.9685815 ↗
29. Wu, X., Wei, S., and Zhou, Y. (2022, January 28). Deep multi-scale representation learning with attention for automatic modulation classification. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy.10.1109/IJCNN55064.2022.9892813 ↗
30. Automatic modulation classification using techniques from image classification10.1049/cmu2.12335 ↗
31. Convolutional neural networks for automatic cognitive radio waveform recognition10.1109/ACCESS.2017.2716191 ↗
32. A learnable distortion correction module for modulation recognition10.1109/LWC.2018.2855749 ↗
33. Fusion image based radar signal feature extraction and modulation recognition10.1109/ACCESS.2019.2892526 ↗
34. Data-driven deep learning for automatic modulation recognition in cognitive radios10.1109/TVT.2019.2900460 ↗
35. Zhang, Q., Xu, Z., and Zhang, P. (2018, January 18–20). Modulation recognition using wavelet-assisted convolutional neural network. Proceedings of the 2018 International Conference on Advanced Technologies for Communications (ATC), Ho Chi Minh City, Vietnam.10.1109/ATC.2018.8587447 ↗
36. Hiremath, S.M., Deshmukh, S., Rakesh, R., and Patra, S.K. (2018, January 28–31). Blind identification of radio access techniques based on time-frequency analysis and convolutional neural network. Proceedings of the TENCON 2018—2018 IEEE Region 10 Conference, Jeju Island, Republic of Korea.10.1109/TENCON.2018.8650355 ↗
37. Convolutional neural network and multi-feature fusion for automatic modulation classification10.1049/el.2019.1789 ↗
38. Blind channel identification aided generalized automatic modulation recognition based on deep learning10.1109/ACCESS.2019.2934354 ↗
39. Fusion methods for CNN-based automatic modulation classification10.1109/ACCESS.2019.2918136 ↗
40. Yongshi, W., Jie, G., Hao, L., Li, L., Zhigang, W., and Houjun, W. (2017, January 20–23). CNN-based modulation classification in the complicated communication channel. Proceedings of the 2017 13th IEEE International Conference on Electronic Measurement &Instruments (ICEMI), Yangzhou, China.10.1109/ICEMI.2017.8265870 ↗
41. Dileep, P., Das, D., and Bora, P.K. (2020, January 21–23). Dense layer dropout based CNN architecture for automatic modulation classification. Proceedings of the 2020 National Conference on Communications (NCC), Kharagpur, India.10.1109/NCC48643.2020.9055989 ↗
42. Robust automated VHF modulation recognition based on deep convolutional neural networks10.1109/LCOMM.2018.2809732 ↗
43. Modulation classification based on signal constellation diagrams and deep learning10.1109/TNNLS.2018.2850703 ↗
44. Wu, H., Wang, Q., Zhou, L., and Meng, J. (2018, January 17). VHF radio signal modulation classification based on convolution neural networks. Proceedings of the 1st International Symposium on Water System Operations, MATEC Web of Conferences, Beijing, China.10.1051/matecconf/201824603032 ↗
45. Peng, S., Jiang, H., Wang, H., Alwageed, H., and Yao, Y.D. (2017, January 7–8). Modulation classification using convolutional neural network based deep learning model. Proceedings of the 2017 26th Wireless and Optical Communication Conference (WOCC), Newark, NJ, USA.10.1109/WOCC.2017.7929000 ↗
46. End-to-end learning from spectrum data: A deep learning approach for wireless signal identification in spectrum monitoring applications10.1109/ACCESS.2018.2818794 ↗
47. Over-the-air deep learning based radio signal classification10.1109/JSTSP.2018.2797022 ↗
48. Longi, K., Pulkkinen, T., and Klami, A. (2017, January 15–17). Semi-supervised convolutional neural networks for identifying wi-fi interference sources. Proceedings of the Ninth Asian Conference on Machine Learning, Seoul, Republic of Korea.
49. Zhang, M., Zeng, Y., Han, Z., and Gong, Y. (2018, January 25–28). Automatic modulation recognition using deep learning architectures. Proceedings of the 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Kalamata, Greece.10.1109/SPAWC.2018.8446021 ↗
50. Sang, Y., and Li, L. (2018, January 26–30). Application of novel architectures for modulation recognition. Proceedings of the 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Chengdu, China.10.1109/APCCAS.2018.8605691 ↗
51. Wang, Z., Sun, D., Gong, K., Wang, W., and Sun, P. (2021). A Lightweight CNN Architecture for Automatic Modulation Classification. Electronics, 10.10.3390/electronics10212679 ↗
52. Training images generation for CNN based automatic modulation classification10.1109/ACCESS.2021.3073845 ↗
53. D-GF-CNN Algorithm for Modulation Recognition10.1007/s11277-021-09391-2 ↗
54. Combining neural networks for modulation recognition10.1016/j.dsp.2021.103264 ↗
55. Learning of Time-Frequency Attention Mechanism for Automatic Modulation Recognition10.1109/LWC.2022.3140828 ↗
56. Ensemble of Convolution Neural Networks for Improving Automatic Modulation Classification Performance
57. West, N.E., and O’shea, T. (2017, January 6–9). Deep architectures for modulation recognition. Proceedings of the 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Baltimore, MD, USA.10.1109/DySPAN.2017.7920754 ↗
58. Deep long short-term memory networks-based automatic recognition of six different digital modulation types under varying noise conditions10.1007/s00521-019-04261-2 ↗
59. Zhang, Y., Tong, L., Zhang, L., and Kan, W. (2018, January 19–21). A deep learning approach for modulation recognition. Proceedings of the 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP), Shanghai, China.10.1109/ICDSP.2018.8631811 ↗
60. Mendis, G.J., Wei, J., and Madanayake, A. (2017, January 27–28). Deep belief network for automated modulation classification in cognitive radio. Proceedings of the 2017 Cognitive Communications for Aerospace Applications Workshop (CCAA), Cleveland, OH, USA.10.1109/CCAAW.2017.8001609 ↗
61. Sun, X., Gao, L., Luo, X., and Su, K. (2016, January 27–29). RBM based cooperative Bayesian compressive spectrum sensing with adaptive threshold. Proceedings of the 2016 IEEE/CIC International Conference on Communications in China (ICCC), Chengdu, China.10.1109/ICCChina.2016.7636844 ↗
62. Automatic modulation classification using gated recurrent residual network10.1109/JIOT.2020.2991052 ↗
63. Multi-modulation recognition using convolution gated recurrent unit networks10.1088/1742-6596/1284/1/012052 ↗
64. Li, J., Qi, L., and Lin, Y. (2016, January 20–22). Research on modulation identification of digital signals based on deep learning. Proceedings of the 2016 IEEE International Conference on Electronic Information and Communication Technology (ICEICT), Harbin, China.10.1109/ICEICT.2016.7879726 ↗
65. Li, M., Li, O., Liu, G., and Zhang, C. (2018). Generative adversarial networks-based semi-supervised automatic modulation recognition for cognitive radio networks. Sensors, 18.10.1109/ICCT.2018.8600032 ↗
66. Deep hierarchical network for automatic modulation classification10.1109/ACCESS.2019.2928463 ↗
67. Liu, X., Yang, D., and El Gamal, A. (November, January 29). Deep neural network architectures for modulation classification. Proceedings of the 2017 51st Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA.10.1109/ACSSC.2017.8335483 ↗
68. A Kind of Wireless Modulation Recognition Method Based on DenseNet and BLSTM10.1109/ACCESS.2021.3111406 ↗
69. Automatic Modulation Recognition Method Based on Hybrid Model of Convolutional Neural Networks and Gated Recurrent Units
70. Automatic modulation recognition based on CNN and GRU10.26599/TST.2020.9010057 ↗
71. CGDNet: Efficient hybrid deep learning model for robust automatic modulation recognition10.1109/LNET.2021.3057637 ↗
72. Wang, N., Liu, Y., Ma, L., Yang, Y., and Wang, H. (2021). Multidimensional CNN-LSTM network for automatic modulation classification. Electronics, 10.10.3390/electronics10141649 ↗
73. Towards recurrent neural network with multi-path feature fusion for signal modulation recognition10.1007/s11276-021-02877-8 ↗
74. Deep learning based modulation recognition with multi-cue fusion10.1109/LWC.2021.3078878 ↗
75. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
76. Recent advances in convolutional neural networks10.1016/j.patcog.2017.10.013 ↗
77. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
78. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
79. Zeiler, M.D., and Fergus, R. (2014). Visualizing and understanding convolutional networks. Computer Vision—ECCV 2014, Springer. Lecture Notes in Computer Science.10.1007/978-3-319-10590-1_53 ↗
80. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
81. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA.10.1109/CVPR.2015.7298594 ↗
82. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
83. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
84. A trainable feature extractor for handwritten digit recognition10.1016/j.patcog.2006.10.011 ↗
85. Backpropagation through time: What it does and how to do it10.1109/5.58337 ↗
86. Fang, W., Jiang, J., Lu, S., Gong, Y., Tao, Y., Tang, Y., Yan, P., Luo, H., and Liu, J. (2020). A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS signal outages. Remote Sens., 12.10.3390/rs12020256 ↗
87. Deep learning10.1038/nature14539 ↗
88. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
89. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.10.3115/v1/D14-1179 ↗
90. Automatic identification of digital modulation types10.1016/0165-1684(95)00099-2 ↗
91. A fast learning algorithm for deep belief nets10.1162/neco.2006.18.7.1527 ↗
92. A novel DBN feature fusion model for cross-corpus speech emotion recognition10.1155/2016/7437860 ↗
93. Jun, C., Qin, Y., and Yi, Z. (2017, January 25–26). Speech signals identification base on improved DBN. Proceedings of the 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China.10.1109/IAEAC.2017.8054192 ↗
94. Shi, P. (2018, January 27–29). Speech emotion recognition based on deep belief network. Proceedings of the 2018 IEEE 15th International Conference on Networking, Sensing and Control (ICNSC), Zhuhai, China.10.1109/ICNSC.2018.8361376 ↗
95. Xie, Y., Zou, C.R., Liang, R.Y., and Tao, H.W. (2016, January 24–26). Phoneme recognition based on deep belief network. Proceedings of the 2016 International Conference on Information System and Artificial Intelligence (ISAI), Hong Kong, China.10.1109/ISAI.2016.0081 ↗
96. Kakkar, D. (2018, January 22–23). Facial expression recognition with LDPP & LTP using deep belief network. Proceedings of the 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India.
97. Regularized deep belief network for image attribute detection10.1109/TCSVT.2016.2539604 ↗
98. Facial expression recognition utilizing local direction-based robust features and deep belief network10.1109/ACCESS.2017.2676238 ↗
99. Fan, R., and Hu, W. (2017, January 29–31). Face recognition with improved deep belief networks. Proceedings of the 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guilin, China.10.1109/FSKD.2017.8393043 ↗
100. Cheng, M. (2015, January 18–20). The cross-field DBN for image recognition. Proceedings of the 2015 IEEE International Conference on Progress in Informatics and Computing (PIC), Nanjing, China.