SavedAdd your journal

Journals / Mühendislik Bilimleri ve Araştırmaları Dergisi / 2025 / Cilt: 7 Sayı: 2

Coverage Area Estimation Using a Multi-Branch 1D Convolutional Neural Network

Çok Dallı 1B Evrişimli Sinir Ağı Kullanarak Kapsama Alanı Tahmini

Uğur Erbaş(BURSA TECHNICAL UNIVERSITY)0000-0002-7552-1949
Tahir Bekiryazıcı(BURSA TECHNICAL UNIVERSITY)0000-0002-0664-649X
Gürkan Aydemir(BURSA TECHNICAL UNIVERSITY)0000-0001-9213-576X
Mehmet Barış Tabakcıoğlu(BURSA TECHNICAL UNIVERSITY)0000-0002-1607-355X
Pages
135–147
Publication Date
2025-10-27
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results show that the proposed model provides high accuracy in coverage estimation and works more efficiently than conventional methods.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In cellular networks, coverage estimation is critical for network planning and optimization.
📊
Key Findings & Data:Deep learning-based methods also accurately predict signal propagation, but are limited in large-scale applications due to the data requirements.
💡
Conclusion & Impact:Experimental results show that the proposed model provides high accuracy in coverage estimation and works more efficiently than conventional methods.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Kapsama Alanı · Derin Evrişimsel Sinir Ağlar · Geometrik Optik

Abstract

In cellular networks, coverage estimation is critical for network planning and optimization. Traditional ray tracing models the propagation of radio waves but faces limitations in large-scale applications due to high computational cost. Deep learning-based methods also accurately predict signal propagation, but are limited in large-scale applications due to the data requirements. In this study, large-scale synthetic datasets are created with Uniform Theory of Diffraction (UTD) based ray tracing simulations to overcome this problem. The proposed method generates 2D coverage maps by analyzing direct, reflected and diffracted electromagnetic propagation paths in 3D digital terrain maps. The developed “Multi-Branch Coverage Estimation Network” aims to estimate the signal propagation accurately and efficiently. Experimental results show that the proposed model provides high accuracy in coverage estimation and works more efficiently than conventional methods. Thus, high quality coverage estimation without the need for real measurements is an important step in wireless network planning.

Özet

Hücresel ağlarda kapsama alanı tahmini, ağ planlaması ve optimizasyonu için kritik önem taşır. Geleneksel ışın izleme, radyo dalgalarının yayılımını modellese de yüksek hesaplama maliyeti nedeniyle büyük ölçekli uygulamalarda sınırlamalarla karşılaşır. Derin öğrenme tabanlı yöntemler de sinyal yayılımını doğru tahmin etmesine karşın, veri gereksinimi nedeniyle geniş ölçekli kullanımlarda kısıtlanır. Bu çalışmada, söz konusu sorunu aşmak amacıyla Uniform Kırınım Teorisi (UTD) tabanlı ışın izleme simülasyonlarıyla büyük ölçekli sentetik veri setleri oluşturulmuştur. Önerilen yöntem, 3D dijital arazi haritalarındaki doğrudan, yansıyan ve kırınıma uğrayan elektromanyetik yayılım yollarını analiz ederek 2D kapsama haritaları üretir. Geliştirilen "Çok Dallı Kapsama Alanı Tahmin Ağı" ise sinyal yayılımını doğru ve verimli şekilde tahmin etmeyi amaçlamaktadır. Deneysel sonuçlar, önerilen modelin kapsama tahmininde yüksek doğruluk sağladığını ve geleneksel yöntemlere göre daha verimli çalıştığını göstermektedir. Böylece gerçek ölçümlere ihtiyaç duymadan yüksek kaliteli kapsama tahmini yapabilmek, kablosuz ağ planlamasında önemli bir adım niteliği taşımaktadır.

🔖

Cite This Article

Erbaş, U., Bekiryazıcı, T., Aydemir, G., Tabakcıoğlu, M. B. (2025). Coverage Area Estimation Using a Multi-Branch 1D Convolutional Neural Network. Mühendislik Bilimleri ve Araştırmaları Dergisi, Cilt: 7 Sayı: 2, 135–147. https://doi.org/10.46387/bjesr.1661104

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (25)

  1. M.B. Tabakcıoğlu, “Coverage Prediction for Triple Diffraction Scenarios”, Aces Journal, vol. 33, no. 11, pp. 1217-1222, 2018.
  2. J.B. Keller, “Geometrical Theory of Diffraction,” Journal of the Optical Society of America, vol. 52, no. 2, pp. 116-130, 1962.
  3. R.G. Kouyoumjian and P.H. Pathak, “A uniform geometrical theory of diffraction for an edge in a perfectly conducting surface,” in Proceedings of the IEEE, vol. 62, no. 11, pp. 1448-1461, Nov., 1974.
  4. M.B. Tabakcioglu, “Extensive Comparison Results of Coverage Map of Optimum Base Station Location of Digital Terrain with UTD Based Model”, Progress In Electromagnetics Research M, vol. 97, pp. 69-76, 2020.
  5. M.B. Tabakcioglu, and A. Kara, “Comparison of Improved Slope UTD Method with UTD based Methods and Physical Optic Solution for Multiple Building Diffractions”, Electromagnetics, vol. 29, no. 4, pp. 303-320, 2009.
  6. M.H. Zadeh, F. Fuschini, M. Barbiroli, V. Degli Esposti, E. Maria Vitucci and S. Del Prete, “Site-Specific Machine Learning Approach for Line of Sight Detection,” 2023 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications, pp. 096-101, Venice, Italy, 2023.
  7. W.R. Loh, S.Y. Lim, I.F.M. Rafie, J.S. Ho and K.S. Tze, “Intelligent Base Station Placement in Urban Areas With Machine Learning,” in IEEE Antennas and Wireless Propagation Letters, vol. 22, no. 9, pp. 2220-2224, Sep., 2023.
  8. T. Nagao and T. Hayashi, “Study on radio propagation prediction by machine learning using urban structure maps,” 2020 14th European Conference on Antennas and Propagation, pp. 1-5, Copenhagen, Denmark, 2020.
  9. I. Iliev, Y. Velchev, P.Z. Petkov, B. Bonev, G. Iliev, and I. Nachev, “A Machine Learning Approach for Path Loss Prediction Using Combination of Regression and Classification Models,” Sensors, vol. 24, no. 17, pp. 5855, 2024.
  10. K. Inoue, K. Ichige, T. Nagao and T. Hayashi, “On The Building Map for Radio Propagation Prediction Using Machine Learning,” 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, pp. 842-847, Helsinki, Finland, 2021.
  11. K. Inoue, K. Ichige, T. Nagao and T. Hayashi, “Learning-Based Prediction Method for Radio Wave Propagation Using Images of Building Maps,” in IEEE Antennas and Wireless Propagation Letters, vol. 21, no. 1, pp. 124-128, Jan., 2022.
  12. S.P. Sotiroudis, K. Siakavara, G.P. Koudouridis, P. Sarigiannidis and S. K. Goudos, “Enhancing Machine Learning Models for Path Loss Prediction Using Image Texture Techniques,” in IEEE Antennas and Wireless Propagation Letters, vol. 20, no. 8, pp. 1443-1447, Aug., 2021.
  13. C. Wang et al., “Channel Path Loss Prediction Using Satellite Images: A Deep Learning Approach,” in IEEE Transactions on Machine Learning in Communications and Networking, vol. 2, pp. 1357-1368, 2024.
  14. U. Erbaş, T. Bekiryazici, G. Aydemir and M. B. Tabakcioğlu, “Coverage Area Estimation Based on Convolutional Neural Networks,” 2024 32nd Signal Processing and Communications Applications Conference, pp. 1-4, Mersin, Turkiye, 2024.
  15. R.-T. Juang, “Explainable Deep-Learning-Based Path Loss Prediction from Path Profiles in Urban Environments,” Applied Sciences, vol. 11, no. 15, pp. 6690, 2021.
  16. T. Hayashi, T. Nagao and S. Ito, “A study on the variety and size of input data for radio propagation prediction using a deep neural network,” 2020 14th European Conference on Antennas and Propagation (EuCAP), pp. 1-5, Copenhagen, Denmark, 2020.
  17. T. Imai, K. Kitao and M. Inomata, “Radio Propagation Prediction Model Using Convolutional Neural Networks by Deep Learning,” 2019 13th European Conference on Antennas and Propagation, pp. 1-5, Krakow, Poland, 2019.
  18. R.G. Dempsey, J. Ethier, and H. Yanikomeroglu, “Map-Based Path Loss Prediction in Multiple Cities Using Convolutional Neural Networks,” IEEE Antennas and Wireless Propagation Letters, pp. 1-5, 2025.
  19. Z. Qiu et al., “CNN-Based Path Loss Prediction With Enhanced Satellite Images,” in IEEE Antennas and Wireless Propagation Letters, vol. 23, no. 1, pp. 189-193, Jan., 2024.
  20. R. Levie, Ç. Yapar, G. Kutyniok, and G. Caire, “RadioUNet: Fast Radio Map Estimation With Convolutional Neural Networks,” IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 4001-4015, June 2021.
  21. A. Marey, M. Bal, H. F. Ates and B. K. Gunturk, “PL-GAN: Path Loss Prediction Using Generative Adversarial Networks,” in IEEE Access, vol. 10, pp. 90474-90480, 2022.
  22. N. Faruk et al., “Path Loss Predictions in the VHF and UHF Bands Within Urban Environments: Experimental Investigation of Empirical, Heuristics and Geospatial Models,” in IEEE Access, vol. 7, pp. 77293-77307, 2019.
  23. T. Tomie, S. Suyama, K. Kitao and M. Nakamura, “Evaluation of High-Performance Radio Propagation Simulation Method in Path Loss Estimation,” 2023 IEEE 97th Vehicular Technology Conference, pp. 1-5, Florence, Italy, 2023.
  24. U. Erbas, M. B. Tabakcioglu, “3D Coverage Mapping with UTD and Geometrical Optic Model,” Journal of Electromagnetics, vol. 7, pp. 4-9, 2024.
  25. U. Erbaş and M. Barış Tabakcioğlu, “Generation of 3D Coverage Map,” 2022 30th Signal Processing and Communications Applications Conference, pp. 1-4, Safranbolu, Turkey, 2022.