AN SVM-BASED PREDICTIVE SYSTEM FOR DETECTION AND FORECASTING OF UNLICENSED FM BROADCASTS

Salihu Ibrahim; Emmanuel  Eronu Majiyebo; Aliyu Ozovehe Sanni; Uthman Muhammad

doi:10.4314/njt.2026.5466

Authors

Salihu Ibrahim Department of Electrical/Electronic Engineering, Faculty of Engineering, University of Abuja, FCT, NIGERIA
Emmanuel Eronu Majiyebo Department of Electrical/Electronic Engineering, Faculty of Engineering, University of Abuja, FCT, NIGERIA
Aliyu Ozovehe Sanni Department of Electrical/Electronic Engineering, Faculty of Engineering, University of Abuja, FCT, NIGERIA
Uthman Muhammad Department of Electrical/Electronic Engineering, Faculty of Engineering, University of Abuja, FCT, NIGERIA

DOI:

https://doi.org/10.4314/njt.2026.5466

Keywords:

Spectrum Interference, Spectrum Monitoring, Unlicensed FM Broadcast, Support Vector Machine, Predictive Enforcement

Abstract

Unlicensed FM broadcasting continues to pose significant risks to national security, communication integrity, and regulatory oversight, particularly in regions where radio remains a vital means of public discourse. This study presents an intelligent, parameter-based system for detecting and forecasting unauthorised FM broadcasts, bypassing the limitations of traditional, content-focused approaches. By integrating Support Vector Machine (SVM) classification with Support Vector Regression (SVR) forecasting, this work introduces a proactive monitoring framework that transitions spectrum governance from reactive detection to predictive enforcement. The system analyses key transmission features—assigned frequencies, band occupancy, and stereo multiplex—to distinguish between licensed and illicit broadcasts, independently of content, language, or programming format. Trained on regulatory data from Nigeria's National Broadcasting Commission, comprising 22,971 raw FM spectrum records collected from Abuja and surrounding states over three years (2021–2023), and pre-processed into 3,169 samples, the model achieved 99.96% accuracy, 100% recall, 100% specificity, and 0% false alarm rate, surpassing existing benchmarks by 0.13%. While this improvement may appear numerically modest, it holds operational significance in large-scale regulatory scenarios where even marginal gains prevent false enforcement actions and reduce resource wastage. The integrated forecasting layer (RMSE=0.042, MAE=0.031) enables pre-emptive identification of interference patterns up to 12 months ahead, demonstrating strong predictive alignment with 2024 interference cases. This work presents a scalable, computationally lightweight, and data-driven solution for spectrum monitoring. It applies beyond Nigeria to spectrum-constrained developing regions, enhancing regulatory capabilities in densely populated environments.

References

[1] Melkote, S. R., and Singhal, A., “Handbook of communication and development,” Edward Elgar Publishing, Cheltenham, UK, 2021.

[2] Apaza, R. D., Knoblock, E. J. and Li, H., “A New Spectrum Management Concept for Future NAS Communications,” in Proc 39th AIAA/IEEE Digital Avionics Systems Conference (DASC), San Antonia, TX, USA, pp 1-8, 2020.

[3] Khan, M. and Pembecioglu, N., “Destructive role of radio in society: Case study of Pakistan (Malakand Region),” Mediterranean Journal of Social Sciences, 6(4S2), pp. 678–688, 2015. doi: 10.5901/mjss.2015.v6n4s2p678.

[4] Shang, J., Liu, Y. and Yan, S., “A System for Data Fusion of Multi-Source Wireless Monitoring Devices and Identification of Illegal FM Broadcast Signals,” in Proc. 10th IEEE International Conference on High Performance and Smart Computing (HPSC), Shenzhen, China, pp. 120–125, 2024. doi: 10.1109/HPSC62738.2024.00029.

[5] Wu, P.W., Huang, L., Ramírez, D., Xiao, Y.H. and So, H. C., “One-Bit Spectrum Sensing for Cognitive Radio,” IEEE Transactions on Signal Processing, 72(1), pp. 549–564, 2024. doi: 10.1109/TSP.2023.3343569.

[6] Malmstedt, J., “Speaking Amplitudes: Dynamical Variation in Swedish Radio Broadcasting, 1980–1998,” Journal of Radio & Audio Media, (ahead-of-print): pp. 1–17, 2025. doi: 10.1080/19376529.2025.2469248.

[7] Ma, J., Liu, H., Peng, C., and Qiu, T., “Unauthorized Broadcasting Identification: A Deep LSTM Recurrent Learning Approach,” IEEE Transactions on Instrumentation and Measurement, 69(9), pp. 5981–5983. 2020. doi: 10.1109/TIM.2020.3008988.

[8] Huang, Z., Liu, W., Li, Z., Shao, Z. and Dong, C., “Intelligent Identification of Illegal Broadcast Based on Distributed Spectrum Monitoring,” in IET 8th International Conference on Wireless, Mobile & Multimedia Networks, Beijing, China, pp. 5–11, 2019.

[9] Cortèš, G, Fonollosa, J., Serrà, J., Pascual, S., and Serra, X., “Baf: an Audio Fingerprinting Dataset for Broadcast Monitoring”,Zenodo, Version 1, 2022. doi: 10.5281/zenodo.6868083.

[10] Guo, S., Xu, Y., Huang, W. and Liu, B., “An SEI-Based Identification Scheme for Illegal FM Broadcast,” in Proc. IEEE 23rd Int. Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Hainan, China, pp. 517–524, 2021. doi: 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00092.

[11] Cortes, C. and Vapnik, V., “Support-vector networks,” Machine Learning, 20(3), pp. 273–297, 1995. doi: 10.1007/BF00994018.

[12] Wang, K., Chen, Y., Bo, D. and Wang, S. “A novel multi-user collaborative cognitive radio spectrum sensing model: Based on a CNN-LSTM model,” PLoS One, 20(1), pp. 1-27, 2025. doi: 10.1371/journal.pone.0316291.

[13] Abdelbaset, S., Kasem, H., Khalaf, A., Hussein, A. and Kabeel, A., “Deep Learning-Based Spectrum Sensing for Cognitive Radio Applications,” Sensors, 24(24): pp. 1–22, 2024. doi: 10.3390/s24247907.

[14] Li, L., Xie, W. and Zhou, X. “Cooperative Spectrum Sensing Based on LSTM-CNN Combination Network in Cognitive Radio System,” IEEE Access, 11, pp. 87615–87625, 2023. doi: 10.1109/ACCESS.2023.3305483.

[15] Wu, J., Qiu, Z., Dai, M., Bao, J., Xu, X. and Cao, W. “Distributed Sequential Detection for Cooperative Spectrum Sensing in Cognitive Internet of Things,” Sensors, 24(2): pp. 1–20, 2024. doi: 10.3390/s24020688.

[16] Kim, J., Parikh, K. and Mason, G. “Distribution of the Analog or Digital FM Composite Multiplex Signal across IP Networks,” in Proc. NAB Show Broadcast Engineering Conference, Las Vegas, NV, USA, pp. 1–8, 2016.

[17] Ajdani, M. and Ghaffary, H. “Design Network Intrusion Detection System Using Support Vector Machine,” International Journal of Communication Systems, 34(3), e4689, 2021. doi: 10.1002/dac.4689.

[18] Rajagopal, S., Kundapur, P. P. and Hareesha, K. S., “A Stacking Ensemble for Network Intrusion Detection Using Heterogeneous Datasets,” Security and Communication Networks, pp. 1–9, 2020. doi: 10.1155/2020/4586875.

[19] Çiftci, B., Çetin, N., Günaydın, S. and Kaplan, M., “Machine Learning Approaches for Binary Classification of Sorghum (Sorghum bicolor L.) seeds from image color features,” Journal of Food Composition and Analysis, 140, p. 107208, 2025. doi: 10.1016/J.JFCA.2025.107208.

[20] Bazzana, F., Bee, M. and Hussin Adam Khatir, A. A., “Machine Learning Techniques for Default Prediction: An Application to Small Italian Companies,” Risk Management, 26(1), pp. 1–28, 2024. doi: 10.1057/s41283-023-00132-2.

[21] Furuse, Y. and Tran, G. K., “Localization of Radio Sources Using High Altitude Platform Station (HAPS),” Sensors, 25(6), p. 1935, 2025. doi: 10.3390/s25061935.

[22] Jagannath, A., Jagannath, J. and Kumar, P. S. P. V., “A Comprehensive Survey on Radio Frequency (RF) Fingerprinting: Traditional Approaches, Deep Learning, and Open Challenges,” Computer Networks, 219: pp. 1–24, 2022. doi: 10.1016/j.comnet.2022.109455.

[23] Nandom, S. S., Abe, G. T. and Gambo, I. P., “Application of Random Forest and Hierarchical Clustering Models for Crop and Fertilizer Recommendation to Farmers,” Nigerian Journal of Technology, 44(1), pp. 114–122, 2025. doi: 10.4314/njt.v44i1.13.

[24] Yang, K., Zhao, L. and Wang, C., “A New Intelligent Bearing Fault Diagnosis Model Based on Triplet Network and SVM,” Scientific Reports, 12(1), pp. 1–15, 2022. doi: 10.1038/s41598-022-08956-w.

[25] Zhang, Y. and Luo, Z., “A Review of Research on Spectrum Sensing Based on Deep Learning,” Electronics (MDPI), 12(21), pp. 1–28, 2023. doi: 10.3390/electronics12214514.

[26] Senol, N. S., Baza, M., Rasheed, A. and Alsabaan, M., “Privacy-Preserving Detection of Tampered Radio-Frequency Transmissions Utilizing Federated Learning in LoRa Networks,” Sensors, 24(22), pp. 1–20, 2024. doi: 10.3390/s24227336.

[27] Sujithra, C and Thandapani, K., “CitZO‐SVM: Machine Learning‐Based Spectrum Sensing and Channel Allocation for Cognitive Radio Networks,” International Journal of Communication Systems, 38(7), e70053, 2025. doi: 10.1002/dac.70053.

[28] Zheng, W., Rong, X., Bao, X. and Dong, Y., “Adaptive Support Vector Machine for Time-Variant Failure Probability Function Estimation. Reliability Engineering & System Safety,” Reliability Engineering & System Safety, 253, pp. 1–12, 2025.

[29] Alnuaimi, A. F. A. H. and Albaldawi, T. H. K., “An Overview of Machine Learning Classification Techniques,” BIO Web of Conferences, 97, p. 00133, 2024. doi: 10.1051/bioconf/20249700133.

[30] Elreedy, D., Atiya, A. F. and Kamalov, F., “A Theoretical Distribution Analysis of Synthetic Minority Oversampling Technique (SMOTE) for imbalanced learning,” Machine Learning, 113(7), pp. 4903–4923, 2024. doi: 10.1007/s10994-022-06296-4.

[31] Aygül, M. A., Çırpan, H. A. and Arslan, H. “Machine Learning-Based Spectrum Occupancy Prediction: A Comprehensive Survey,” Frontiers in Communications and Networks, 6, pp. 1–35, 2025. doi: 10.3389/frcmn.2025.1482698.

[32] Buchwald, J., Yeang, C. P., Stemeroff, N., Barton, J. and Harrington, Q., “What Heinrich Hertz Discovered about Electric Waves in 1887–1888,” Archive for History of Exact Sciences, 75(2), pp. 125–171, 2021. doi: 10.1007/s00407-020-00260-1.

[33] Irfan, M., Sciancalepore, S. and Oligeri, G. “On the Reliability of Radio Frequency Fingerprinting,” 2024, [Online]. Available: http://arxiv.org/abs/2408.09179

[34] Akram, J., Akram, A., Ingle, P., Jhaveri, R. H., Anaissi, A. and Akhunzada, A. “Privacy-Preserving Spatial Crowdsourcing Drone Services for Postdisaster Infrastructure Monitoring: A Conditional Federated Learning Approach,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, pp. 16272–16291, 2025. doi: 10.1109/JSTARS.2025.3577648.

[35] International Telecommunication Union, “Radio Regulations, Edition of 2024, Geneva”, Switzerland, 2024. Accessed: 22, 2025. [Online]. Available: https://www.itu.int/pub/R-REG-RR

[36] Bharati, R. K. Handbook on the Information Technology Act, 2000: Offences, Penalties, and the Impact of New Criminal Laws, Deep Science Publishing, New Delhi, India, 2025. doi: 10.70593/978-93-7185-183-1.

[37] Gupta, M. S., Srivastava, A. and Kumar, K. “PORA: A Proactive Optimal Resource Allocation Framework for Spectrum Management in Cognitive Radio Networks,” IEEE Transactions on Network and Service Management, 22(4), pp. 3249–3261, 2025, doi: 10.1109/TNSM.2025.3540717

[38] Brown, C. and Rutagemwa, H., “Revolutionizing Spectrum Management: Data-Driven Strategies,” IEEE Wireless Communications, 32 (4): pp. 1–9, 2025. doi: 10.1109/MWC.004.2500029

[39] Lahrouni, K., Semlali, H., Andrieux, G., Diouris, J.F. and Ghammaz, A., “A Systematic Literature Review on Spectrum Detection for Cognitive Radio-Internet of Things Networks,” Ad Hoc Networks, 175, 103857, 2025. doi: 10.1016/j.adhoc.2025.103857.

[40] Labsis, L., Teguig, D., Lassami, N. and Chikh Touami, H., “An Advanced Blind Cyclostationary Spectrum Sensing Algorithm for Cognitive Radio Networks,” Physica Scripta, 100(6), 065502, 2025. doi: 10.1088/1402-4896/adcfd0.

[41] Casmin, E. and Oliveira, R., “Survey on Context-Aware Radio Frequency-Based Sensing,” Sensors, 25(3), 602, 2025, doi: 10.3390/s25030602

[42] African Telecommunications Union, “Framework for Harmonized Spectrum Management in Africa,” Nairobi, Kenya, 2023. Accessed: 2025. [Online]. Available: https://atuuat.africa/en/documents

[43] United Nations, “Transforming Our World: The 2030 Agenda for Sustainable Development ,” New York, NY, USA: United Nations, 2015.

[44] Shalev-Shwartz, S., “Online Learning and Online Convex Optimization,” Foundations and Trends in Machine Learning, 4(2), pp. 107–194, 2011. doi: 10.1561/2200000018.

[45] Ahmed, Md. T., Haque, M., Sugiura, Y. and Shimamura, T. “Machine Learning Approach to Energy Detection Based Spectrum Sensing for Cognitive Radio Networks,” IEEJ Transactions on Electrical and Electronic Engineering, 20(6), pp. 910–919, 2025. doi: 10.1002/tee.24261.

[46] Zhou, K., Li, Q., Cai, P., Cai, Z., Shi, X., and Wang, F., “Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting,” IEEE Internet of Things Journal, (early access): pp. 1–13, 2025. doi: 10.1109/JIOT.2025.3594571.