A Fast Automatic Modulation Classification Based on STFT Using Hybrid Deep Neural Network

Document Type : Research Paper


Faculty of Electrical and Computer Engineering University of Tabriz, Tabriz, Iran


Automatic modulation classification is used in various applications, including satellite communication systems, military communication, and submarine communications. In this paper, the automatic classification of modulation types is done using a two-stage method that combines a short-time Fourier transform (STFT) and a hybrid deep neural network (HDNN). At the first stage, using the STFT as a data source, the time-frequency information is retrieved from the modulated signals. A hybrid deep neural network feed two-dimensional (2D) images as inputs. In the second stage, the HDNN feeds the 2D time-frequency data to classify the various modulation types. Six various types of modulation schemes, including amplitude-shift keying, frequency-shift keying, phase-shift keying, quadrature amplitude-shift keying, quadrature frequency-shift keying, and quadrature phase-shift keying, are recognized automatically in the SNR range of 0 to 25 dB. An exhaustive computer simulation has been performed to evaluate the performance of the proposed digital modulation classification method. The simulation results show that, in comparison with the existing methods, our proposed method performs well and significantly reduces the processing time.


[1] X. Hao and et al.‏, "Automatic Modulation Classification via Meta-Learning‏," IEEE Internet of Things Journal, vol. 10, no. 14, pp. 12276-12292, July 2023.
[2] C. Lin, W. Yan, L. Zhang, and W. Wang, "A real-time modulation recognition system based on software-defined radio and multi-skip residual neural network," IEEE Access, vol. 8, pp. 221235–221245, Dec. 2020.
[3] B. Ramkumar, "Automatic modulation classification for cognitive radios using cyclic feature detection," IEEE Circuits and Systems Magazine, vol. 9, no. 2, pp. 27–45, June 2009.
[4] Q. Zheng, X. Tian, Z. Yu, H. Wang, A. Elhanashi, and S. Saponara, "DL-PR: Generalized automatic modulation classification method based on deep learning with priori regularization," Eng. Appl. Artif. Intell., vol. 122, p. 106082, June 2023.
[5] H. Tayakout, I. Dayoub, K. Ghanem, and H. Bousbia-Salah, "Automatic modulation classification for D-STBC cooperative relaying networks," IEEE Wirel. Commun. Lett., vol. 7, no. 5, pp. 780–783, April 2018.
[6] S. Huang, C. Lin, K. Zhou, Y. Yao, H. Lu, and F. Zhu, "Identifying physical-layer attacks for IoT security: An automatic modulation classification approach using multi-module fusion neural network," Phys. Commun., vol. 43, pp. 1–10, Dec. 2020.
[7] J. Zheng and Y. Lv, "Likelihood-based automatic modulation classification in OFDM with index modulation," IEEE Trans. Veh. Technol., vol. 67, no. 9, pp. 8192–8204, Sept. 2018.
[8] A. Kumar, S. Majhi, G. Gui, H. C. Wu, and C. Yuen, "A Survey of Blind Modulation Classification Techniques for OFDM Signals," Sensors, vol. 22, no. 3, pp. 1–32, Jan. 2022.
[9] L. Xie and Q. Wan, "Cyclic Feature-Based Modulation Recognition Using Compressive Sensing," IEEE Wirel. Commun. Lett., vol. 6, no. 3, pp. 402–405, June 2017.
[10] L. Han, F. Gao, Z. Li, and O. A. Dobre, "Low Complexity Automatic Modulation Classification Based on Order-Statistics," IEEE Trans. Wirel. Commun., vol. 16, no. 1, pp. 400–411, Jan. 2017.
[11] R. Gupta, S. Majhi, and O. A. Dobre, "Design and Implementation of a Tree-Based Blind Modulation Classification Algorithm for Multiple-Antenna Systems," IEEE Trans. Instrum. Meas., vol. 68, no. 8, pp. 3020–3031, Aug. 2019.
[12] R. Gupta, S. Kumar, and S. Majhi, "Blind Modulation Classification for Asynchronous OFDM Systems over Unknown Signal Parameters and Channel Statistics," IEEE Trans. Veh. Technol., vol. 69, no. 5, pp. 5281–5292, May 2020.
[13] K. Triantafyllakis, M. Surligas, G. Vardakis, and S. Papadakis, "Phasma: An automatic modulation classification system based on Random Forest," In 2017 IEEE Int. Symp. Dyn. Spectr. Access Networks (DySPAN), pp. 1-3, March 2017.
[14] H. Tayakout, F. Z. Bouchibane, and E. Boutellaa, "On the Performance of Digital Modulation Classification for Cooperative Multiple Relays Network System without Direct Channel," in 2022 2nd International Conference on Advanced Electrical Engineering (ICAEE), pp. 1–5, Oct. 2022.
[15] W. Zhang, "Automatic modulation classification based on statistical features and Support Vector Machine," 2014 31th URSI Gen. Assem. Sci. Symp. URSI GASS 2014, no. 2, pp. 1–4, Aug. 2014.
[16] M. O. Mughal and S. Kim, "Signal classification and jamming detection in wide-band radios using naïve bayes classifier," IEEE Commun. Lett., vol. 22, no. 7, pp. 1398–1401, July 2018.
[17] O. Russakovsky, and et al., "ImageNet Large Scale Visual Recognition Challenge," Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, April 2015.
[18] C. Gan, L. Wang, and Z. Zhang, “Multi-entity sentiment analysis using self-attention based hierarchical dilated convolutional neural network,” Futur. Gener. Comput. Syst., vol. 112, pp. 116–125, Nov. 2020.
[19] H. Mohana and M. Suriakala, "An Enhanced Prospective Jaccard Similarity Measure (PJSM) to Calculate the User Similarity Score Set for E-Commerce Recommender System," In Intelligent System Design: Proceedings of Intelligent System Design: INDIA 2019, vol. 1171 pp. 129–142, Aug. 2021.
[20] C. Luo, K. Zhang, S. Salinas, and P. Li, "SecFact: Secure Large-scale QR and LU Factorizations," IEEE Trans. Big Data, vol. 7, no. 4, pp. 796–807, Oct. 2021.
[21] H. Ye, L. Liang, G. Y. Li, and B.-H. Juang, "Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels," IEEE Trans. Wirel. Commun., vol. 19, no. 5, pp. 3133–3143, May 2020.‏
[22] T. J. O’Shea, J. Corgan, and T. C. Clancy, "Convolutional radio modulation recognition networks," Commun. Comput. Inf. Sci., vol. 629, pp. 213–226, Aug. 2016.
[23] T. J. O’Shea, T. Roy, and T. C. Clancy, "Over-the-Air Deep Learning Based Radio Signal Classification," IEEE J. Sel. Top. Signal Process., vol. 12, no. 1, pp. 168–179, Feb. 2018.
[24] K. Yashashwi, A. Sethi, and P. Chaporkar, "A Learnable Distortion Correction Module for Modulation Recognition," IEEE Wirel. Commun. Lett., vol. 8, no. 1, pp. 77–80, Feb. 2019.
[25] T. Zhang, C. Shuai, and Y. Zhou, "Deep Learning for Robust Automatic Modulation Recognition Method for IoT Applications," IEEE Access, vol. 8, pp. 117689–117697, March 2020.
[26] J. Shi, S. Hong, C. Cai, Y. Wang, H. Huang, and G. Gui, "Deep Learning-Based Automatic Modulation Recognition Method in the Presence of Phase Offset," IEEE Access, vol. 8, pp. 42831–42847, March 2020.
[27] S. Peng and et al., "Modulation Classification Based on Signal Constellation Diagrams and Deep Learning," IEEE Trans. Neural Networks Learn. Syst., vol. 30, no. 3, pp. 718–727, July 2018.
[28] C. Hou, Y. Li, X. Chen, and J. Zhang, "Automatic modulation classification using KELM with joint features of CNN and LBP," Phys. Commun., vol. 45, p. 101259, April 2021.
[29] S. Rajendran, W. Meert, D. Giustiniano, V. Lenders, and S. Pollin, "Deep learning models for wireless signal classification with distributed low-cost spectrum sensors," IEEE Trans. Cogn. Commun. Netw., vol. 4, no. 3, pp. 433–445, May 2018.
[30] M. M. Elsagheer and S. M. Ramzy, "A hybrid model for automatic modulation classification based on residual neural networks and long short term memory," Alexandria Engineering Journal, vol. 67, pp. 117-128, March 2023.
[31] F. Wang, T. Shang, C. Hu, and Q. Liu, "Automatic Modulation Classification Using Hybrid Data Augmentation and Lightweight Neural Network," Sensors, vol. 23, no. 9, p. 4187, April 2023.
[32] R. G. Gallager, Principles of digital communication, Cambridge, UK: Cambridge University Press, 2008.‏
[33] R. He, Q. Chen, and W. He, "Study on compressed sensing imaging based on intensity modulation in Fourier domain," Optik, vol. 125, no. 14, pp. 3759-3763, July 2014.
[34] L. Zhou, Z. Sun, and W. Wang, "Learning to short-time Fourier transform in spectrum sensing." Physical Communication, vol. 25, pp. 420-425, Dec. 2017.‏
[35] J. L. Semmlow, Biosignal and Medical Image Processing, CRC press, Oct. 2004.
[36] Ö. F. Alçin, S. Siuly, V. Bajaj, Y. Guo, A. Şengür, and Y. Zhang, "Multi category EEG signal classification developing time-frequency texture features-based Fisher vector encoding method," Neurocomputing, vol. 218, pp. 251-258, Dec. 2016.
[37] N. Daldal, Z. Cömert, and K. Polat, "Automatic determination of digital modulation types with different noises using Convolutional Neural Network based on time–frequency information," Applied Soft Computing Journal, vol. 86, p. 105834, Jan. 2020.
[38] C. Du, S. Gao, Y. Liu, and B. Gao, "Multi-focus image fusion using deep support value convolutional neural network," Optik, vol. 176, pp. 567–578, Jan. 2019.
[39] Z. Zhao, Y. Zhang, Z. Comert, and Y. Deng, "Computer-Aided Diagnosis System of Fetal Hypoxia Incorporating Recurrence Plot With Convolutional Neural Network," Frontiers in physiology, vol. 10, pp. 1–14, March 2019.
[40] R. Zhou, F. Liu, and C. W. Gravelle, "Deep Learning for Modulation Recognition: A Survey with a Demonstration," IEEE Access, vol. 8, pp. 67366–67376, April 2020.
[41] I. H. Sarker, "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions," SN Comput. Sci., vol. 2, no. 6, pp. 1–20, Aug. 2021.
[42] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
[43] C. Nicholson, Evaluation metrics for machine learning—Accuracy, precision, recall, and F1 defined, https://wiki.pathmind.com/accuracy-precision-recall-f1 (2019). Accessed Nov. 2023.