Advances and Emerging Challenges of Digital Modulation Recognition for Wireless Signals Using Artificial Intelligence Techniques

This paper discusses a statistical review of various artificial intelligence techniques used in wireless communication for the implementation of automatic modulation recognition of digital modulated signals. Automatic recognition of modulation types from received signals in communication systems reduces complexity and cost of circuit design of the demodulators used at receiver. It helps to design an adaptive universal communication receiver in a noisy medium, where the behavior of a modulated signal keeps on changing continuously with noise. For the effective usage of RF (radio frequency) spectrum, determination of modulation types in spectrum sensing and software defined radios (SDRs) is considered to be crucial. Demodulation and recognition of signal types using hybrid machine learning algorithms at receiving end plays very significant role in various applications of cognitive radios, satellite communication systems, and military intelligence and in underwater surveillance systems too. Implementation methodologies of these applications for automatic recognition of modulation types are discussed using various AI techniques. Various spectral and statistical parameters like time-frequency features, higher order cumulants, constellation images and cyclic frequency domain features extracted from received signals for classifying modulation types are summarized. Different algorithms developed to extract features, classification algorithms and the validation metrics used in the models are outlined. Methodologies used to distinguish the type of digital modulated signals like ASK, PSK, FSK and QAM signals with its inferences and analysis from datasets are discussed.

Automatic Modulation Recognition (AMR), Transfer learning (TL), Self Learning (SL)

1. Azzouz, E. E., & Nandi, A. K. (1995). Automatic identification of digital modulation types. Signal Processing, 47(1), 55-69. [Google Scholar] [Crossref]

2. Ma, H., Xu, G., Meng, H., Wang, M., Yang, S., Wu, R., & Wang, W. (2020). Cross Model Deep Learning Scheme for Automatic Modulation Classification. IEEE Access, 8, 78923-78931. [Google Scholar] [Crossref]

3. Daldal, N., Cömert, Z., & Polat, K. (2020). Automatic determination of digital modulation types with different noises using Convolutional Neural Network based on time–frequency information. Applied Soft Computing, 86, 105834. [Google Scholar] [Crossref]

4. Shah, M. H., & Dang, X. (2020). Low-complexity deep learning and RBFN architectures for modulation classification of space-time block-code (STBC)-MIMO systems. Digital Signal Processing, 99, 102656. [Google Scholar] [Crossref]

5. Iglesias, V., Grajal, J., & Yeste-Ojeda, O. (2011, August). Automatic modulation classifier for military applications. In 2011 19th European Signal Processing Conference (pp. 1814-1818). IEEE. [Google Scholar] [Crossref]

6. Xue, Y., Jin, Y., Chen, S., Du, H., & Shen, G. (2024). Modulation signal automatic recognition technology combining truncated migration processing and CNN. IEEE Access, vol. 12, pp. 120414-120428, 2024, https://doi.org/10.1109/ACCESS.2024.3448397. [Google Scholar] [Crossref]

7. Ramkumar, B. (2011). Automatic Modulation Classication and Blind Equalization for Cognitive Radios (Doctoral dissertation, Virginia Tech). [Google Scholar] [Crossref]

8. Singer, A. C., Nelson, J. K., & Kozat, S. S. (2009). Signal processing for underwater acoustic communications. IEEE Communications Magazine, 47(1), 90-96. [Google Scholar] [Crossref]

9. Ali, A. K., & Erçelebi, E. (2020). Automatic modulation recognition of DVB-S2X standard-specific with an APSK-based neural network classifier. Measurement, 151, 107257. [Google Scholar] [Crossref]

10. Li, P. (2019). Research on radar signal recognition based on automatic machine learning. Neural Computing and Applications, 1-11. [Google Scholar] [Crossref]

11. Soliman, S. S., & Hsue, S. Z. (1992). Signal classification using statistical moments. IEEE Transactions on Communications, 40(5), 908-916. [Google Scholar] [Crossref]

12. Rosti, A. V. (1998). Statistical methods in modulation classification. Master of Science Thesis, Tampere University of Technology, Finland June [Google Scholar] [Crossref]

13. Su, W. (2013). Feature space analysis of modulation classification using very high-order statistics. IEEE Communications Letters, 17(9), 1688-1691. [Google Scholar] [Crossref]

14. Yan, X., Zhang, G., & Wu, H. C. (2018). A Novel Automatic Modulation Classifier Using Graph-Based Constellation Analysis for ${M} $-ary QAM. IEEE Communications Letters, 23(2), 298-301. [Google Scholar] [Crossref]

15. Spooner, C. M., Mody, A. N., Chuang, J., & Petersen, J. (2017, March). Modulation recognition using second-and higher-order cyclostationarity. In 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN) (pp. 1-3). IEEE. [Google Scholar] [Crossref]

16. Jiang, X. R., Chen, H., Zhao, Y. D., & Wang, W. Q. (2020). Automatic modulation recognition based on mixed-type features. International Journal of Electronics, 1-10. [Google Scholar] [Crossref]

17. West, N. E., & O'Shea, T. (2017, March). Deep architectures for modulation recognition. In 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN) (pp. 1-6). IEEE. [Google Scholar] [Crossref]

18. Abdelmutalab, A., Assaleh, K., & El-Tarhuni, M. (2016). Automatic modulation classification based on high order cumulants and hierarchical polynomial classifiers. Physical Communication, 21, 10-18. [Google Scholar] [Crossref]

19. Nandi, A. K., & Azzouz, E. E. (1998). Algorithms for automatic modulation recognition of communication signals. IEEE Transactions on communications, 46(4), 431-436. [Google Scholar] [Crossref]

20. Goldsmith, A. (2005). Wireless communications. Cambridge university press. [Google Scholar] [Crossref]

21. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105) [Google Scholar] [Crossref]

22. Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural networks. In Advances in neural information processing systems (pp. 971-980). [Google Scholar] [Crossref]

23. Harp, G. R., Richards, J., Tarter, S. S. J. C., Mackintosh, G., Scargle, J. D., Henze, C., ... & Voien, J. (2019). Machine Vision and Deep Learning for Classification of Radio SETI Signals. arXiv preprint arXiv:1902.02426. [Google Scholar] [Crossref]

24. Gao, L., Zhang, X., Gao, J., & You, S. (2019). Fusion image based radar signal feature extraction and modulation recognition. IEEE Access, 7, 13135-13148 [Google Scholar] [Crossref]

25. Xu, Y., Li, D., Wang, Z., Guo, Q., & Xiang, W. (2019). A deep learning method based on worsignals. Wireless Networks, 25(7), 3735-3746. [Google Scholar] [Crossref]

26. Yazan, E., & Talu, M. F. (2017, September). Comparison of the stochastic gradient descent based optimization techniques. In 2017 International Artificial Intelligence and Data Processing Symposium (IDAP) (pp. 1-5). IEEE. [Google Scholar] [Crossref]

27. Zhu, X., & Fujii, T. (2017, January). A modulation classification method in cognitive radios system using stacked denoising sparse autoencoder. In 2017 IEEE Radio and Wireless Symposium (RWS) (pp. 218-220). IEEE. [Google Scholar] [Crossref]

28. O’Shea, T. J., Corgan, J., & Clancy, T. C. (2016, September). Convolutional radio modulation recognition networks. In International conference on engineering applications of neural networks (pp. 213-226). Springer, Cham. [Google Scholar] [Crossref]

29. O’Shea, T. J., Roy, T., & Clancy, T. C. (2018). Over-the-air deep learning based radio signal classification. IEEE Journal of Selected Topics in Signal Processing, 12(1), 168-179. [Google Scholar] [Crossref]

30. JG, P. (2001). Digital communications. Me Graw-Hill, 777-778. [Google Scholar] [Crossref]

31. Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural networks. In Advances in neural information processing systems (pp. 971-980). [Google Scholar] [Crossref]

32. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026-1034). [Google Scholar] [Crossref]

33. Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural networks. In Advances in neural information processing systems (pp. 971-980). [Google Scholar] [Crossref]

34. Su, W. (2013). Feature space analysis of modulation classification using very high-order statistics. IEEE Communications Letters, 17(9), 1688-1691. [Google Scholar] [Crossref]

35. Hashim, I. A., Abdul Sadah, J. W., Saeed, T. R., & Ali, J. K. (2015). Recognition of QAM signals with low SNR using a combined threshold algorithm. IETE Journal of Research, 61(1), 65-71. [Google Scholar] [Crossref]

36. Wang, Y., Zhang, H., Sang, Z., Xu, L., Cao, C., & Gulliver, T. A. (2019). Modulation classification of underwater communication with deep learning network. Computational intelligence and neuroscience, 2019. [Google Scholar] [Crossref]

37. Hoang, D. A., Nguyen, H., & Le, T. N. (2025). Performance analysis of superposition M-ary QAM modulation in coded protograph LDPC MIMO communication systems with low-resolution ADCs. IEEE Access, vol. 13, pp. 107410-107428, 2025, https://doi.org/10.1109/ACCESS.2025.3581775 [Google Scholar] [Crossref]

38. Chen, Z., Wang, J., & Zheng, Y. R. (2016). Frequency-domain turbo equalization with iterative channel estimation for MIMO underwater acoustic communications. IEEE Journal of Oceanic Engineering, 42(3), 711-721. [Google Scholar] [Crossref]

39. Ye, H., Li, G. Y., & Juang, B. H. (2017). Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters, 7(1), 114-117. [Google Scholar] [Crossref]

40. Xu, Y., Li, D., Wang, Z., Guo, Q., & Xiang, W. (2019). A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals. Wireless Networks, 25(7), 3735-3746. [Google Scholar] [Crossref]

41. Gao, L., Zhang, X., Gao, J., & You, S. (2019). Fusion image based radar signal feature extraction and modulation recognition. IEEE Access, 7, 13135-13148. [Google Scholar] [Crossref]

42. Zuo, L., Li, M., & Xia, X. G. (2016). New smoothed time-frequency rate representations for suppressing cross terms. IEEE Transactions on Signal Processing, 65(3), 733-747. [Google Scholar] [Crossref]

43. Choi, H. I., & Williams, W. J. (1989). Improved time-frequency representation of multicomponent signals using exponential kernels. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(6), 862-871. [Google Scholar] [Crossref]

44. Stankovic, L. (1995). A method for improved distribution concentration in the time-frequency analysis of multicomponent signals using the L-Wigner distribution. IEEE Transactions on Signal Processing, 43(5), 1262-1268. [Google Scholar] [Crossref]

45. Zhang, X., Li, X., & Feng, Y. (2016). A new multifocus image fusion based on spectrum comparison. Signal Processing, 123, 127-142. [Google Scholar] [Crossref]

46. Daldal, N., Cömert, Z., & Polat, K. (2020). Automatic determination of digital modulation types with different noises using Convolutional Neural Network based on time–frequency information. Applied Soft Computing, 86, 105834. [Google Scholar] [Crossref]

47. Zhu, Z., & Nandi, A. K. (2015). Automatic modulation classification: principles, algorithms and applications. John Wiley & Sons. [Google Scholar] [Crossref]

48. Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of research and development, 3(3), 210-229. [Google Scholar] [Crossref]

49. Blum, A., & Mitchell, T. (1998, July). Combining labeled and unlabeled data with co-training. In Proceedings of the eleventh annual conference on Computational learning theory (pp. 92-100). [Google Scholar] [Crossref]

50. Uys, L. Y., Gouws, M., Strydom, J. J., & Helberg, A. S. (2017, September). The performance of feature-based classification of digital modulations under varying SNR and fading channel conditions. In 2017 IEEE AFRICON (pp. 198-203). IEEE. [Google Scholar] [Crossref]

51. Liu, Y., Liang, G., Xu, X., & Li, X. (2008, October). The methods of recognition for common used M-ary digital modulations. In 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing (pp. 1-4). IEEE. [Google Scholar] [Crossref]

52. Al-Nuaimi, D. H., Hashim, I. A., Zainal Abidin, I. S., Salman, L. B., & Mat Isa, N. A. (2019). Performance of feature-based techniques for automatic digital modulation recognition and classification—A review. Electronics, 8(12), 1407. [Google Scholar] [Crossref]

53. Zhang, D., Ding, W., Liu, C., Wang, H., & Zhang, B. (2020). Modulated Autocorrelation Convolution Networks for Automatic Modulation Classification Based on Small Sample Set. IEEE Access, 8, 27097-27105. [Google Scholar] [Crossref]

54. Blossom, E. (2004). GNU radio: tools for exploring the radio frequency spectrum. Linux journal, 2004(122), 4. [Google Scholar] [Crossref]

55. Holland, O., Bogucka, H., & Medeisis, A. (2015). Opportunistic spectrum sharing and white space access: The practical reality. John Wiley & Sons. [Google Scholar] [Crossref]

56. Chen, S., Zhang, Y., He, Z., Nie, J., & Zhang, W. (2020). A novel attention cooperative framework for automatic modulation recognition. IEEE Access, 8, 15673-15686. [Google Scholar] [Crossref]

• Communication Strategies among Promoters During MATTA Fair 2025
• An Examination of Colleen Ballinger’s Experience in Social Media: Cancel Culture Chronicle
• Communication Patterns in Conflict Interactions in Premarital Couples Who Are in Abusive Relationships
• Social Media Use on Mental Health Outcomes among Adolescents and Young Adults in Port Harcourt City
• (Un)Successful Error Repairs in L2 Communication