Email the author SPECTROGRAM BASED INTERFERENCE DETECTION USING SOFTWARE DEFINED RADIO
Abstract
Software defined radio (SDR) platforms enable flexible and cost-effective radio frequency (RF) monitoring, supporting detection and classification of interference across diverse wireless environments. In this work, a SDR-based interference detection and classification framework is presented, focusing on two widely used frequency bands: the FM band (88–110 MHz) and the 2.4 GHz ISM band. A novel over-the-air dataset of labeled spectrograms was collected using low-cost SDR hardware and GNU Radio, emulating idle spectrum and three representative interference types: burst noise, continuous wave, and chirp signals. A convolutional neural network (CNN) was designed and evaluated under multiple configurations, investigating the impact of different optimization solvers and activation functions on classification performance. Experimental results demonstrate very high accuracy for interference detection (binary classification) in both frequency bands, exceeding 98% on the test datasets. For multi-class interference type classification, the model achieves up to 98% accuracy in the FM band, while reduced performance is observed in the 2.4 GHz band due to time–frequency resolution limitations inherent to spectrogram-based representations for higher signal bandwidths. The results highlight the effectiveness of deep learning for SDR-based interference monitoring, while also emphasizing the trade-offs between computational efficiency and discriminative capability when using spectrogram representations in wideband wireless systems.
Full Text:
PDFReferences
Molla, Dereje M., Hakim Badis, Laurent George, and Marion Berbineau. 2022. Software Defined Radio Platforms for Wireless Technologies. IEEE Access 10: 26203–29. https://doi.org/10.1109/access.2022.315436
Helbet Robert, Bechet Paul, M. Simona and Sarbu Annamaria. Real Time Broadband Electromagnetic Spectrum Monitoring System based on Software Defined Radio Technology. 2021 9th International Conference on Modern Power Systems (MPS) (2021): 1-6. https://doi.org/10.1109/MPS52805.2021.9492577.
Huijie Zhu, Binhui Chen, Yiteng Wang and Lijun Wang. Ultra-Wideband Spectrum Monitoring Using Software Defined Radio. 2022 IEEE 22nd International Conference on Communication Technology (ICCT) (2022): 251-254. https://doi.org/10.1109/ICCT56141.2022.10072513.
M. Sorecau, E. Sorecău, A. Sarbu, R. Helbet and P. Bechet. Electromagnetic spectrum monitoring of LTE channels based on SDR portable sensor: preliminary analysis. IOP Conference Series: Materials Science and Engineering, 1254 (2022). https://doi.org/10.1088/1757-899X/1254/1/012009.
R. Helbet, P. Bechet, Vasile Monda, S. Miclaus and Iulian Bouleanu. Low-Cost Sensor Based on SDR Platforms for TETRA Signals Monitoring. Sensors (Basel, Switzerland), 21 (2021). https://doi.org/10.3390/s21093160.
Yassine Ben-Aboud, M. Ghogho, S. Pollin and A. Kobbane. Electro-Smog Monitoring Using Low-Cost Software-Defined Radio Dongles. IEEE Access, 9 (2021): 107149-107158. https://doi.org/10.1109/ACCESS.2021.3100773.
Chang Ge, Zuchao Li, He Gong, Maoyuan Sun, Kun Li and Mengguan Pan. Software Defined Radio-Based Electromagnetic Environment Interference Detection. 2024 IEEE 7th International Conference on Electronic Information and Communication Technology (ICEICT) (2024): 95-98.
https://doi.org/10.1109/ICEICT61637.2024.10671219.
Lu, Hui, Ruoliu Zhang, and Kefei Mao. 2025. LS-Based Multipath Channel Measurement Method Using Software Defined Radio Platform. Measurement 241 (February): 115712.
https://doi.org/10.1016/j.measurement.2024.115712.
Marc García-Bermúdez, Jordi Solé-Lloveras and Marco A. Azpúurua. Interference Evaluation on Software Defined Radio Links using the Amplitude Probability Distribution. 2024 International Symposium on Electromagnetic Compatibility – EMC Europe (2024): 284-289.
https://doi.org/10.1109/EMCEurope59828.2024.10722059.
Le, Quoc Nam, Tan Quoc Huynh, Hien Quang Ta, Phuoc Vo Tan, and Lap Luat Nguyen. 2024. Modified Receiver Architecture in Software-Defined Radio for Real-Time Modulation Classification. EURASIP Journal on Advances in Signal Processing 2024 (1). https://doi.org/10.1186/s13634-024-01176-6.
E. Sorecău, M. Sorecau, Alexandru-Marius Vasile and P. Bechet. Advanced Military Radio Channels Monitoring System Based on Software Defined Radio Platform: Preliminary Analysis. International conference KNOWLEDGE-BASED ORGANIZATION, 29 (2023): 107 - 112. https://doi.org/10.2478/kbo-2023-0083.
Le, Quoc Nam, Hien Q. Ta, Khuong Ho-Van, and Lap Luat Nguyen. 2025. Real-Time Modulation Classification Architecture in Software Defined Radio. Physical Communication 68 (February): 102573. https://doi.org/10.1016/j.phycom.2024.102573.
Radu, Florin, Petru A. Cotfas, Marian Alexandru, Titus C. Bălan, Vlad Popescu, and Daniel T. Cotfas. 2023. Signals Intelligence System with Software-Defined Radio. Applied Sciences 13 (8): 5199. https://doi.org/10.3390/app13085199.
C. Politis, S. Maleki, J. M. Duncan, J. Krivochiza, S. Chatzinotas and Björn Ottesten. SDR Implementation of a Testbed for Real-Time Interference Detection With Signal Cancellation. IEEE Access, 6 (2018): 20807-20821. https://doi.org/10.1109/ACCESS.2018.2825885.
Fred Taylor, Evan Gattis, Lucca Trapani, Dennis M Akos, Sherman C. Lo, Todd Walter and Yu‐Hsuan Chen. Software Defined Radio for GNSS Radio Frequency Interference Localization. Sensors (Basel, Switzerland), 24 (2023). https://doi.org/10.3390/s24010072.
Pany, Thomas, Dennis Akos, Javier Arribas, et al. 2024. GNSS Software-Defined Radio: History, Current Developments, and Standardization Efforts. NAVIGATION: Journal of the Institute of Navigation 71 (1): navi.628. https://doi.org/10.33012/navi.628.
Adomnitei, C.-I., C.-E. Lesanu, A. Done, E. Coca, and A. Lavric. 2024. Phased Antenna Arrays, Software Defined Radio and Artificial Intelligence: Advancing LEO Satellite Communications. Advances in Electrical and Computer Engineering 24 (4): 57–64. https://doi.org/10.4316/aece.2024.04006.
Peters, Edwin Gerardus Wilhelmus, and Craig R. Benson. 2020. A Doppler Correcting Software Defined Radio Receiver Design for Satellite Communications. IEEE Aerospace and Electronic Systems Magazine 35 (2): 38–48. https://doi.org/10.1109/maes.2019.2960952.
Manco, Julio, Iyad Dayoub, Amor Nafkha, Mohammad Alibakhshikenari, and Hayfa Ben Thameur. 2022. Spectrum Sensing Using Software Defined Radio for Cognitive Radio Networks: A Survey. IEEE Access 10: 131887–908. https://doi.org/10.1109/access.2022.3229739
Phull, Jaskaran Singh, Narwant Singh Grewal, Simar Preet Singh, and Asha Rani. 2021. Implementation and Performance Analysis of Cognitive Radio with Frequency Updating Algorithm on Software-Defined Radio Platform. Recent Advances in Electrical and Electronic Engineering (Formerly Recent Patents on Electrical and Electronic Engineering) 14 (3): 268–75. https://doi.org/10.2174/2352096514999201224124958.
Lin, Yih-Chuan, and Zhe-Sheng Shih. 2018. Design and Simulation of a Radio Spectrum Monitoring System with a Software-Defined Network. Computers and Electrical Engineering 68 (May): 271–85.
https://doi.org/10.1016/j.compeleceng.2018.03.043.
Daniel Gaydos, P. Nayeri and R. Haupt. Adaptive Beamforming with Software-Defined-Radio Arrays. IEEE Access, 10 (2022): 11669-11678. https://doi.org/10.1109/access.2022.3144959
Hugues Vasseur, Gilles Nzokira and Bart Desoete. On-board detection, localization, and mitigation of radio frequency interference. 38th International Communications Satellite Systems Conference (ICSSC 2021), 2021 (2021): 220-225. https://doi.org/10.1049/icp.2022.0575.
Andreas Andersson, P. Eliardsson, Erik Axell, Kristoffer Hägglund and K. Wiklundh. Deep Learning-Based In-Band Interference Detection and Classification. IEEE Transactions on Electromagnetic Compatibility, 66 (2024): 1958-1966. https://doi.org/10.1109/temc.2024.3449434.
Hamda Bouzabia, Georges Kaddoum and Tri Nhu Do. Deep Learning-Based Interference Detection, Classification, and Forecasting Algorithm for ESM Radar Systems. IEEE Access, 12 (2024): 148120-148142. https://doi.org/10.1109/ACCESS.2024.3475732.
Charl D Du Toit, T. L. Grobler and Danie Ludick. A comparison framework for deep learning RFI detection algorithms. Monthly Notices of the Royal Astronomical Society (2024). https://doi.org/10.1093/mnras/stae892.
Alireza Vafaei Sadr, B. Bassett, N. Oozeer, Y. Fantaye and Chris Finlay. Deep learning improves identification of Radio Frequency Interference. Monthly Notices of the Royal Astronomical Society, 499 (2020): 379-390. https://doi.org/10.1093/MNRAS/STAA2724
C. P. Robinson, Daniel Uvaydov, Salvatore D’oro and T. Melodia. Narrowband Interference Detection via Deep Learning. ICC 2023 - IEEE International Conference on Communications (2023): 6379-6384. https://doi.org/10.1109/ICC45041.2023.10278618.
Wei Dai and Changpeng Ji. Modulation Recognition System of Electromagnetic Interference Signal Based on SDR. Telecom (2024). https://doi.org/10.3390/telecom5030046.
Electromagnetic Interference Dataset, Kaggle, UCI Machine Learning, accessed September 16, 2025, https://www.kaggle.com/datasets/ucimachinelearning/electromagnetic-interference-dataset/data
Zhongtao Luo, RD Image Dataset for OTHR Interference Detection, IEEE Dataport, April 3, 2022, doi:10.21227/sxem-6z65
Weize Meng, Zhaowen Zeng, Hang Zhu, Ming Tan, Shaowei Wu and Shiqi Xing. Realization of Linear Frequency Modulated short range detection system based on Software Defined Radio. 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC) (2022): 1-5. https://doi.org/10.1109/ctisc54888.2022.9849778.
D. Zuo, C. Shi, K. Jin, P. Zhao, W. Zou and K. Cai, A Machine Learning GNSS Interference Detection Method based on ADS-B Multi-index Features, 2023 Integrated Communication, Navigation and Surveillance Conference (ICNS), Herndon, VA, USA, 2023, pp. 1-11, doi: 10.1109/ICNS58246.2023.10124266.
Z. Liu, S. Lo, and T. Walter, GNSS Interference Detection Using Machine Learning Algorithms on ADS-B Data, in Proc. ION GNSS+ 2021, Stanford University, 2021. Available: https://web.stanford.edu/group/scpnt/gpslab/pubs/papers/Liu_IONGNSS2021_ADS_B.pdf
Ramchandra, A.R.; Skurdal, A.; Ranganathan, P.; Semke, W. Detecting GPS Interference Using Automatic Dependent Surveillance-Broadcast Data. Electronics 2024, 13, 3145. https://doi.org/10.3390/electronics13163145
S. Daoud, G. Eappen, F. Ortiz, E. Lagunas, W. Martins and S. Chatzinotas, CNN-Based on-Board Interference Detection in Satellite Systems: AN Analysis of Dataset Impact on Performance, 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSPW59220.2023.10193395.
Falih, M. S., Abdullah, H. N. (2022). A Spectrum Sensing Profile Based SDR for Cognitive Radio System: An Experimental Work. In Communications in Computer and Information Science (pp. 282–295). Springer International Publishing. https://doi.org/10.1007/978-3-030-97255-4_21
Refbacks
- There are currently no refbacks.
