Autors: Iliev, I. G., Velchev, Y. S., Petkov, P. Ж., Bonev, B. G., Iliev, G. L., Nachev, I. N.
Title: A Machine Learning Approach for Path Loss Prediction Using Combination of Regression and Classification Models
Keywords: LoRa, neural network classification, neural network regression, path loss prediction, radio propagation modeling

Abstract: One of the key parameters in radio link planning is the propagation path loss. Most of the existing methods for its prediction are not characterized by a good balance between accuracy, generality, and low computational complexity. To address this problem, a machine learning approach for path loss prediction is presented in this study. The novelty is the proposal of a compound model, which consists of two regression models and one classifier. The first regression model is adequate when a line-of-sight scenario is fulfilled in radio wave propagation, whereas the second one is appropriate for non-line-of-sight conditions. The classification model is intended to provide a probabilistic output, through which the outputs of the regression models are combined. The number of used input parameters is only five. They are related to the distance, the antenna heights, and the statistics of the terrain profile and line-of-sight obstacles. The proposed approach allows creation of a generalized model that is valid for various types of areas and terrains, different antenna heights, and line-of-sight and non line-of-sight propagation conditions. An experimental dataset is provided by measurements for a variety of relief types (flat, hilly, mountain, and foothill) and for rural, urban, and suburban areas. The experimental results show an excellent performances in terms of a root mean square error of a prediction as low as (Formula presented.) dB and a coefficient of determination as high as 0.702. Although the study covers only one operating frequency of 433 (Formula presented.) (Formula presented.), the proposed model can be trained and applied for any frequency in the decimeter wavelength range. The main reason for the choice of such an operating frequency is because it falls within the range in which many wireless systems of different types are operating. These include Internet of Things (IoT), machine-to-machine (M2M) mesh radio networks, power efficient communication over long distances such as Low-Power Wide-Area Network (LPWAN)—LoRa, etc.

References

  1. Green D. Yun Z. Iskander M.F. Path Loss Characteristics in Urban Environments Using Ray-Tracing Methods IEEE Antennas Wirel. Propag. Lett. 2017 16 3063 3066 10.1109/LAWP.2017.2761299
  2. Qian J. Wu Y. Saleem A. Zheng G. Path Loss Model for 3.5 GHz and 5.6 GHz Bands in Cascaded Tunnel Environments Sensors 2022 22 4524 10.3390/s22124524 35746306
  3. Longley A. Rice P. Prediction of Tropospheric Radio Transmission Loss Over Irregular Terrain: A Computer Method-1968 ESSA Technical Report Institute for Telecommunication Sciences Boulder, CO, USA 1968
  4. Iliev I.G. Bonev B.G. Propagation Loss Model for Mobile Wireless Communication Systems Proceedings of the 2022 57th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST) Ohrid, North Macedonia 16–18 June 2022 1 4 10.1109/ICEST55168.2022.9828669
  5. Faruk N. Popoola S.I. Surajudeen-Bakinde N.T. Oloyede A.A. Abdulkarim A. Olawoyin L.A. Ali M. Calafate C.T. Atayero A.A. Path Loss Predictions in the VHF and UHF Bands Within Urban Environments: Experimental Investigation of Empirical, Heuristics and Geospatial Models IEEE Access 2019 7 77293 77307 10.1109/ACCESS.2019.2921411
  6. ETSI Study on Channel Model for Frequencies from 0.5 to 100 GHz Technical Report 3GPP TR 38.901 version 16.1.0 Release 16 European Telecommunications Standards Institute Valbonne, France 2020
  7. Rappaport T. Wireless Communications: Principles and Practice 2nd ed. Prentice Hall PTR Paramus, NJ, USA 2001
  8. Dalela C. Tuning Of Cost-231 Hata Model for Radio Wave Propagation Predictions Proceedings of the The Second International Conference on Computer Science, Engineering and Applications Delhi, India 25–27 May 2012 Volume 2 255 267 10.5121/csit.2012.2227
  9. Har D. Watson A. Chadney A. Comment on diffraction loss of rooftop-to-street in COST 231-Walfisch-Ikegami model IEEE Trans. Veh. Technol. 1999 48 1451 1452 10.1109/25.790519
  10. Lee W.C.Y. Mobile Communications Design Fundamentals 2nd ed. John Wiley & Sons, Inc. Hoboken, NJ, USA 1992
  11. Jo H.S. Park C. Lee E. Choi H.K. Park J. Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process Sensors 2020 20 1927 10.3390/s20071927 32235640
  12. Nguyen C. Cheema A.A. A Deep Neural Network-Based Multi-Frequency Path Loss Prediction Model from 0.8 GHz to 70 GHz Sensors 2021 21 5100 10.3390/s21155100 34372343
  13. He R. Gong Y. Bai W. Li Y. Wang X. Random Forests Based Path Loss Prediction in Mobile Communication Systems Proceedings of the 2020 IEEE 6th International Conference on Computer and Communications (ICCC) Chengdu, China 11–14 December 2020 1246 1250 10.1109/ICCC51575.2020.9344905
  14. Tahat A. Edwan T. Al-Sawwaf H. Al-Baw J. Amayreh M. Simplistic Machine Learning-Based Air-to-Ground Path Loss Modeling in an Urban Environment Proceedings of the 2020 Fifth International Conference on Fog and Mobile Edge Computing (FMEC) Paris, France 20–23 April 2020 158 163 10.1109/FMEC49853.2020.9144965
  15. Saleh T. Petrov D. Tirkkonen O. Räisänen V. Probabilistic Path Loss Predictors for mmWave Networks Proceedings of the 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring) Virtual 25–28 April 2021 1 6 10.1109/VTC2021-Spring51267.2021.9448967
  16. Kwon B. Son H. Accurate Path Loss Prediction Using a Neural Network Ensemble Method Sensors 2024 24 304 10.3390/s24010304 38203166
  17. Ojo S. Sari A. Ojo T. Path Loss Modeling: A Machine Learning Based Approach Using Support Vector Regression and Radial Basis Function Models Open J. Appl. Sci. 2022 12 990 1010 10.4236/ojapps.2022.126068
  18. George G. Idogho J. Path loss prediction based on machine learning techniques: Support vector machine, artificial neural network, and multi linear regression model J. Phys. Sci. 2022 3 1 22 10.52417/ojps.v3i2.393
  19. Elmezughi M. Salih O. Afullo T. Duffy K. Path loss modeling based on neural networks and ensemble method for future wireless networks Heliyon 2023 9 e19685 10.1016/j.heliyon.2023.e19685 37809436
  20. Elmezughi M.K. Salih O. Afullo T.J. Duffy K.J. Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels Sensors 2022 22 4967 10.3390/s22134967 35808457
  21. Turan B. Coleri S. Machine Learning Based Channel Modeling for Vehicular Visible Light Communication IEEE Trans. Veh. Technol. 2021 70 9659 9672 10.1109/TVT.2021.3107835
  22. Popoola S.I. Atayero A.A. Arausi O.D. Matthews V.O. Path loss dataset for modeling radio wave propagation in smart campus environment Data Brief 2018 17 1062 1073 10.1016/j.dib.2018.02.026 29876462
  23. OSM Buildings 2024 Available online: https://osmbuildings.org (accessed on 28 August 2024)
  24. Manca V. Artificial Neural Network Learning, Attention, and Memory Information 2024 15 387 10.3390/info15070387
  25. Dubey S.R. Singh S.K. Chaudhuri B.B. Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark arXiv 2022 cs.LG/2109.14545 10.1016/j.neucom.2022.06.111
  26. Cortes C. Mohri M. Rostamizadeh A. L2 Regularization for Learning Kernels Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 Montreal, QC, Canada 18–21 June 2009
  27. Semtech Corporation SX1276/77/78/79—137 MHz to 1020 MHz Low Power Long Range Transceiver, 2020. Rev. 7 – May 2020 Available online: https://semtech.my.salesforce.com/sfc/p/#E0000000JelG/a/2R0000001Rbr/6EfVZUorrpoKFfvaF_Fkpgp5kzjiNyiAbqcpqh9qSjE (accessed on 5 September 2024)
  28. Huggins J.S. Mast Mountable Antenna U.S. Patent US20170201002A1 13 July 2017
  29. Ellingson S.W. The modified j-pole: A wideband end-fed half-wave dipole for a VHF reflector feed system Proceedings of the 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting San Diego, CA, USA 9–14 July 2017 773 775 10.1109/APUSNCURSINRSM.2017.8072429
  30. Chawla N.V. Bowyer K.W. Hall L.O. Kegelmeyer W.P. SMOTE: Synthetic Minority Over-sampling Technique J. Artif. Intell. Res. 2002 16 321 357 10.1613/jair.953
  31. Noel M.M. Banerjee A. D G.B.A. Muthiah-Nakarajan V. Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks arXiv 2023 cs.NE/2303.09935
  32. Wu D. Zhu G. Ai B. Application of artificial neural networks for path loss prediction in railway environments Proceedings of the 2010 5th International ICST Conference on Communications and Networking in China Beijing, China 25–27 August 2010 1 5
  33. Phillips C. Sicker D. Grunwald D. Bounding the error of path loss models Proceedings of the 2011 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN) Chennai, India 28 February–3 March 2011 71 82 10.1109/DYSPAN.2011.5936271

Issue

Sensors, vol. 24, 2024, , https://doi.org/10.3390/s24175855

Вид: статия в списание, публикация в реферирано издание, индексирана в Scopus и Web of Science