IRO Journals
IRO Journal on Sustainable Wireless Systems

Classification of RF Signal Using Deep Learning

Open Access
Published: 23 July, 2026
Pages: 207-220
  • Subahari M. , Subahari M.
    Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Madurai, India
    Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Madurai, India
  • Sajeev Senthil , Sajeev Senthil
    Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, India
    Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, India
  • Kishore Pandi C. Kishore Pandi C.
    Department of Biomedical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
    Department of Biomedical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
view PDF
view PDF

How to Cite

M., Subahari, Sajeev Senthil, and Kishore Pandi C. 2026. “Classification of RF Signal Using Deep Learning”. IRO Journal on Sustainable Wireless Systems 8 (3): 207-20. https://doi.org/10.36548/jsws.2026.3.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Automatic Modulation Classification (AMC)
Convolutional Long Short-Term Memory Deep Neural Network (CLDNN)
Radio Frequency Signal Classification
In-Phase and Quadrature (I/Q) Signals
Bit Error Rate (BER)
Intelligent Wireless Communication Systems

Abstract

Automatic Modulation Classification (AMC) is a fundamental component of intelligent wireless communication systems that guarantees robust recognition of modulation types in complex Radio Frequency (RF) channels. This research proposes an end-to-end RF communication model based on a Convolutional Long Short-Term Memory Deep Neural Network (CLDNN) for AMC and communication performance estimation. The RadioML 2016.10a dataset including eleven modulation types was normalized and trained via a novel hybrid CLDNN network which consists of feature extraction module using convolution and temporal sequences learning model. The proposed framework implements not only the classical classification procedure but also synthesis of I/Q signals, their transmission through the TCP channel, and receiver performance evaluation via Bit Error Rate (BER). The obtained experimental results showed 62.48% validation accuracy at 10 dB SNR, while signal reconstruction guaranteed the real-world application of the proposed approach.

References

  1. Dobre, Octavia A., Ali Abdi, Yeheskel Bar-Ness, and Wei Su. "Survey of Automatic Modulation Classification Techniques: Classical Approaches and New Trends." IET Communications, 2007, vol 1, no. 2: 137-156.
  2. Kim, Byeoungdo, Jaekyum Kim, Hyunmin Chae, Dongweon Yoon, and Jun Won Choi. "Deep Neural Network-Based Automatic Modulation Classification Technique." International Conference on Information and Communication Technology Convergence (ICTC), IEEE, 2016: 579-582.
  3. Meng, Fan, Peng Chen, Lenan Wu, and Xianbin Wang. "Automatic Modulation Classification: A Deep Learning Enabled Approach." IEEE Transactions on Vehicular Technology, 2018, vol 67, no. 11: 10760-10772.
  4. Emam, Ayman, M. Shalaby, Mohamed Atta Aboelazm, Hossam E. Abou Bakr, and Hany AA Mansour. "A Comparative Study Between CNN, LSTM, and CLDNN Models in the Context of Radio Modulation Classification." 12th International Conference on Electrical Engineering (ICEENG), IEEE, 2020: 190-195.
  5. Sainath, Tara N., Oriol Vinyals, Andrew Senior, and Haşim Sak. "Convolutional, Long Short-Term Memory, Fully Connected Deep Neural Networks." International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2015: 4580-4584.
  6. Xing, Huijun, Xuhui Zhang, Shuo Chang, Jinke Ren, Zixun Zhang, Jie Xu, and Shuguang Cui. "Joint Signal Detection and Automatic Modulation Classification via Deep Learning." IEEE Transactions on Wireless Communications, 2024, vol 23, no. 11: 17129-17142.
  7. Vagollari, Adela, Viktoria Schram, Wayan Wicke, Martin Hirschbeck, and Wolfgang Gerstacker. "Joint Detection and Classification of RF Signals Using Deep Learning." 93rd Vehicular Technology Conference (VTC2021-Spring), IEEE, 2021: 1-7.
  8. Kaleem, Zeeshan. "Lightweight and Computationally Efficient YOLO for Rogue UAV Detection in Complex Backgrounds." IEEE Transactions on Aerospace and Electronic Systems, 2024, vol 61, no. 2: 5362-5366.
  9. Nelega, Raluca, Romulus Valeriu Flaviu Turcu, Bogdan Belean, and Emanuel Puschita. "Radio Frequency-Based Drone Detection and Classification using Deep Learning Algorithms." International Conference on Software, Telecommunications and Computer Networks (SoftCOM), IEEE, 2023: 1-6.
  10. Shi, Yi, Kemal Davaslioglu, Yalin E. Sagduyu, William C. Headley, Michael Fowler, and Gilbert Green. "Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments." In 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), IEEE, 2019: 1-10.
  11. T. J. O'Shea and J. Corgan, DeepSig RadioML 2016.10a Dataset, DeepSig Inc., 2016. Available: https://www.deepsig.ai/datasets/