Deep Learning based Real Time Radio Signal Modulation Classification and Visualization

Full Text (PDF, 704KB), PP.30-37

Views: 0 Downloads: 0

Author(s)

S. Rajesh 1,* S. Geetha 1 Babu Sudarson S 1 Ramesh S 1

1. Department of Information Technology, Mepco Schlenk Engineering College, Sivakasi, Tamilnadu, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2023.05.04

Received: 20 Apr. 2022 / Revised: 4 Jul. 2022 / Accepted: 1 Aug. 2022 / Published: 8 Oct. 2023

Index Terms

Deep learning, CNN, LSTM, Visualization, LeNet, ResNet, Airspy

Abstract

Radio Modulation Classification is implemented by using the Deep Learning Techniques. The raw radio signals where as inputs and can automatically learn radio features and classification accuracy. The LSTM (Long short-term memory) based classifiers and CNN (Convolutional Neural Network) based classifiers were proposed in this paper. In the proposed work, two CNN based classifiers are implemented such as the LeNet classifier and the ResNet classifier. For visualizing the radio modulation, a class activation vector (w) is used. Finally in the proposed work, it is performed the classification by using the Deep learning models like CNN and LSTM based modulation classifiers. These deep learning models extract the important radio features that are used for classification. Here, the bench mark dataset RadioML2016.10a is used. This is an open dataset which contains the modulated signal I and Q values fewer than ten modulation categories. After evolution of proposed model with bench mark dataset, it is applied with real time data collected through the SDR Dongle receiver. From the obtained real time signal, the modulation categories have been classified and visualized the radio features extracted from the radio modulation classifiers.

Cite This Paper

S. Rajesh, S. Geetha, Babu Sudarson S, Ramesh S, "Deep Learning based Real Time Radio Signal Modulation Classification and Visualization", International Journal of Engineering and Manufacturing (IJEM), Vol.13, No.5, pp. 30-37, 2023. DOI:10.5815/ijem.2023.05.04

Reference

[1]G. Hinton,Y. LeCun and Y. Bengio, “Deep learning,” Nature, vol. 521,no. 7553, May 2015.
[2]A. K. Nandi and E. Azzouz, “Automatic analogue modulation recognition,” Signal Process., vol. 46, no. 2, pp. 211–222, Oct. 1995.
[3]B. M. Sadler and A. Swami, “Hierarchical digital modulation classification using cumulants,” IEEE Trans. Commun., vol. 48, no. 3,pp. 416–429, Mar. 2000.
[4]S. Glisic, S. Majhi, R. Gupta and W. Xiang, “Hierarchical hypothesis and feature-based blind modulation classification for linearly modulated signals,” IEEE Trans. Veh. Technol., vol. 66, no. 12, Dec. 2017.
[5]S. Pollin, V. Lenders, S. Rajendran, W. Meert and D. Giustiniano, “Deep learning models for wireless signal classification with distributed low cost spectrum sensors,” IEEE Trans. Cogn. Commun. Netw., vol. 4,pp. 433–445, Sep. 2018.
[6]Y. Liu and C. Yang, “Modulation recognition with graph convolutional network,” IEEE Wireless Commun. Lett., vol. 9, 624–627, May 2020.
[7]S. Peng et al., “Modulation classiļ¬cation based on signal constellation diagrams and deep learning,” IEEE Trans. Neural Netw. Learn. Syst., vol. 30,pp. 718–727, Mar. 2019.
[8]T. C. Clancy,T. J. O’Shea and J. Corgan “Convolutional radio modulation recognition networks,” in Proc. Int. Conf. Eng. Appl. Neural Netw., 2016, pp. 213–226.
[9]T. J. O’Shea, T. C. Clancy and T. Roy, “Over the air deep learning based radio signal classification,” IEEE J. Sel. Topics Signal Process.,vol. 12,, pp. 168–179, Feb. 2018.
[10]L. Huang,Y. Wu,Y. Zhang, L. Qian, W. Pan and N. Gao, “Data augmentation for deep learning-based radio modulation classification,” IEEE Access, pp. 1498–1506, 2020.
[11]Y. Iwahori, J. Zhang,K. Jiang , H. Wu and A. Wang, , “A novel digital modulation recognition algorithm based on deep convolutional neural network,” Appl. Sci., vol. 10, no. 3, Feb. 2020.
[12]D. Batra, A. Das, M. Cogswell, R. Vedantam, D. Parikh, and R. R. Selvaraju, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. ICCV, pp. 618–626, 2017.
[13]A. Vedaldi and R. C. Fong, “Interpretable explanations of black boxes by meaningful perturbation,” in Proc. ICCV, 2017.
[14]S.Geetha and V. Kalaivani, "Kafka based LSTM Model for Streaming Data Prediction", AIP Conference Proceedings, Vol.2444, Issue.020001, pp.200011-200016, March-2022, DOI: https://doi.org/10.1063/5.0078348.
[15]Usman Mohammed, Tologon Karataev, Omotayo O. Oshiga, Suleiman U. Hussein, Sadiq Thomas, " Comparison of Linear Quadratic – Regulator and Gaussian – Controllers’ Performance, LQR and LQG: Ball-on-Sphere System as a Case Study ", International Journal of Engineering and Manufacturing (IJEM), Vol.11, No.3, pp. 45-67, 2021. DOI: 10.5815/ijem.2021.03.05.