A novel solution for an SDR-based anti-radiation seeker integrating CNN-based RF fingerprint recognition with DOA estimation
7 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.FMC.2026.173-181Keywords:
Anti-radiation seeker; SDR; RF fingerprinting; CNN; DOA estimation; Emitter identification.Abstract
Anti-radiation seekers play an important role in passive detection and localization of hostile RF emitters. This paper proposes an SDR-based anti-radiation seeker architecture integrating convolutional neural network (CNN)-based RF fingerprint identification with MUSIC-based DOA estimation. Received I/Q signals are converted into normalized log-differential spectrograms for CNN-based emitter classification, while synchronized two-channel measurements provide spatial information for MUSIC processing. The two branches are combined to generate a joint emitter–direction output for target discrimination. A proof-of-concept experiment was conducted at 915 MHz using three transmitters configured with identical nominal frequency, bandwidth, transmit power, and waveform parameters. A total of 10,000 samples were collected across multiple acquisition sessions, of which 3,000 were held out for testing. The CNN achieved an overall classification accuracy of 90.37% with a mean confidence of 0.8775, while the MUSIC-based DOA estimator achieved a mean absolute angular error of 2.2518°. These results demonstrate the feasibility of combining RF fingerprint identification and spatial estimation within the proposed seeker-oriented SDR architecture under the tested conditions.
References
[1]. N. F. Palumbo, “Guest Editor’s Introduction: Homing Missile Guidance and Control”, Johns Hopkins APL Technical Digest, Vol. 29, No. 1, pp. 2–11, (2010).
[2]. S. K. Güvenç, “Range To-Go Estimation for a Tactical Missile with a Passive Seeker”, M.S. Thesis, Department of Aerospace Engineering, Middle East Technical University, Ankara, Turkey, (2015).
[3]. B. C. Babaoğlu, “A Method for Estimating Target Velocity and Range with Passive Seeker Data”, M.S. Thesis, Department of Aerospace Engineering, Middle East Technical University, Ankara, Turkey, (2018).
[4]. J. Mitola, “Software Radios: Survey, Critical Evaluation and Future Directions”, IEEE Aerospace and Electronic Systems Magazine, Vol. 8, No. 4, pp. 25–36, (1993). DOI: https://doi.org/10.1109/62.210638
[5]. G. Shen, J. Zhang, A. Marshall, L. Peng and X. Wang, “Radio Frequency Fingerprint Identification for LoRa Using Spectrogram and CNN”, Proceedings of IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, pp. 1–10, (2021). DOI: https://doi.org/10.1109/INFOCOM42981.2021.9488793
[6]. S. Luo, “Deep Learning Based RFF Identification for LoRa”, Teaching Demonstration, King’s College London, (2020).
[7]. G. Shen, J. Zhang, A. Marshall and J. Cavallaro, “Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa”, IEEE Transactions on Information Forensics and Security, Vol. 17, pp. 774–787, (2022). DOI: 10.1109/TIFS.2022.3152404. DOI: https://doi.org/10.1109/TIFS.2022.3152404
[8]. I. Goodfellow, Y. Bengio and A. Courville, “Deep Learning”, MIT Press, Cambridge, MA, USA, (2016).
[9]. Y. LeCun, Y. Bengio and G. Hinton, “Deep Learning”, Nature, Vol. 521, pp. 436–444, (2015). DOI: https://doi.org/10.1038/nature14539
[10]. A. V. Oppenheim and R. W. Schafer, “Discrete-Time Signal Processing”, 3rd ed., Pearson, Upper Saddle River, NJ, USA, (2010).
[11]. S. Haykin, “Communication Systems”, 4th ed., John Wiley & Sons, New York, NY, USA, (2001).
[12]. R. O. Schmidt, “Multiple Emitter Location and Signal Parameter Estimation”, IEEE Transactions on Antennas and Propagation, Vol. AP-34, No. 3, pp. 276–280, (1986). DOI: https://doi.org/10.1109/TAP.1986.1143830
[13]. H. L. Van Trees, “Optimum Array Processing: Part IV of Detection, Estimation, and Modulation Theory”, Wiley-Interscience, New York, NY, USA, (2002). DOI: https://doi.org/10.1002/0471221104
[14]. L. V. Bao, N. Q. Vinh, and P. C. Tu, “Direction estimation and tracking of rapidly moving RF emitters”, Journal of Military Science and Technology, vol. 107, no. 107, pp. 3–12, (2025), doi: 10.54939/1859-1043.j.mst.107.2025.3-12. DOI: https://doi.org/10.54939/1859-1043.j.mst.107.2025.3-12
[15]. N. T. Thien, H. H. Cuong, T. Q. Hien, N. M. Hung, and D. D. Dien, “Broadband signal source localization using convolutional neural networks combined with coherent signal subspace methods”, Journal of Military Science and Technology, no. IITE, pp. 115–122, (2025), doi: 10.54939/1859-1043.j.mst.IITE.2025.115-122. DOI: https://doi.org/10.54939/1859-1043.j.mst.IITE.2025.115-122
