A Gaussian Process Regression Model to Predict Path Loss for an Urban Environment

Full Text (PDF, 1453KB), PP.10-21

Views: 0 Downloads: 0


Seyi E. Olukanni 1,* Ikechi Risi 2 Salifu. F. U. 1 Johnson Oladipupo S. 3

1. Department of Physics, Confluence University of Science and Technology Osara, Nigeria

2. Department of Physics, Rivers State University, Port Harcourt, Nigeria

3. Department of Statistics, Kogi State Poly Technique, Lokoja, Nigeria

* Corresponding author.

DOI: https://doi.org/10.5815/ijmsc.2023.02.02

Received: 1 Feb. 2023 / Revised: 10 Mar. 2023 / Accepted: 18 Apr. 2023 / Published: 8 May 2023

Index Terms

Gaussian process regression, wireless communication, Path Loss, Machine Learning, regression


This research paper presents a Gaussian process regression (GPR) model for predicting path loss signal in an urban environment. The Gaussian process regression model was developed using a dataset of path loss signal measurements acquired in two urban environments in Nigeria. Three different kernel functions were selected and compared for their performance in the Gaussian process regression model, including the squared exponential kernel, the Matern kernel, and the rotational quadratic kernel. The GPR model was validated and evaluated using various performance metrics and compared with different regression models. The results show that the Gaussian process regression model with the Matern kernel outperforms the linear regression and the support vector regression, but the decision tree and the random forest regression did better than the GPR in both cities. In the city of Port Harcourt, the GPR has a RMSE value of 3.0776 dB, the DTR has 2.0005 dB, the SVR has 3.6047 dB, the RFR has 1.0459 dB, and the LR 3.5947dB. The proposed GPR model provides more accurate and efficient approach to predict path loss compared to traditional methods. The extensive data collection and analysis conducted has resulted in a well-developed and accurate model.

Cite This Paper

Seyi E. Olukanni, Ikechi Risi, Salifu. F. U., Johnson Oladipupo S., "A Gaussian Process Regression Model to Predict Path Loss for an Urban Environment", International Journal of Mathematical Sciences and Computing(IJMSC), Vol.9, No.2, pp. 10-21, 2023. DOI: 10.5815/ijmsc.2023.02.02


[1]J. S. Seybold, Introduction to RF Propagation. John Wiley & Sons, Inc, 2005.
[2]D. Ali and O. F. Iloabuchi, “Wavelet Based Residual Method of Detecting GSM Signal Strength Fading,” World Acad. Sci. Eng. Technol. Int. J. Electron. Commun. Eng., vol. 8, no. 9, pp. 1633–1636, 2014.
[3]“An introduction of Gaussian processes and deep Gaussian processes and their application to speech processing,” Acoust. Sci. Technol., vol. 41, no. 2, p. 2020, 2020.
[4]Z. Nadir, M. Bait-suwailam, and M. Idrees, “Pathloss Measurements and Prediction using Statistical Models,” MATEC Web Conf., vol. 05006, pp. 4–7, 2016, doi: DOI: 10.1051/matec conf/20165405006 Pathloss.
[5]O. O. Erunkulu, A. M. Zungeru, S. Member, K. Caspar, and J. M. Chuma, “Cellular Communications Coverage Prediction Techniques : A Survey and Comparison,” IEEE Access, 2020, doi: 10.1109/ACCESS.2020.3003247.
[6]R. A. Valenzuela, “A Ray Tracing Approach to Predicting Indoor Wireless Transmission.”
[7]M. Chen, U. Challita, W. Saad, C. Yin, M. Debbah, and H. F. R, “Artificial Neural Networks-Based Machine Learning for Wireless Networks : A Tutorial,” no. Ml.
[8]J. Q. Shi and T. Choi, Gaussian Process Regression Analysis for Functional Data. New York: Taylor & Francis Group, LLC, 2011.
[9]C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning. Massachusetts: MIT Press, 2006.
[10]N. Yang and Y. Zhang, “A Gaussian Process Classification and Target Recognition Algorithm for SAR Images,” Hindawi Sci. Program., vol. 2022, 2022, doi: https://doi.org/10.1155/2022/9212856.
[11]N. Zhang, J. Xiong, J. Zhong, and K. Leatham, “Gaussian Process Regression Method for Classification for High-Dimensional Data with Limited Samples,” Interntional Conf. Inf. Sci. Technol., 2018, doi: 10.1109/ICIST.2018.8426077.
[12]J. Isabona and D. O. Ojuh, “Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates,” I. J. Math. Sci. Comput., vol. 2, no. June, pp. 14–23, 2021, doi: 10.5815/ijmsc.2021.02.02.
[13]H.-S. Jo, C. Park, E. Lee, H. K. Choi, and J. Park, “Path Loss Prediction Based on Machine Learning Techniques : Principal Component Analysis , Artificial Neural Network , and Gaussian Process,” MDPI sensors, vol. 20, pp. 1–23, 2020, doi: 10.3390/s20071927.
[14]K. J. Jang et al., “Path Loss Model Based on Machine Learning Using Multi-Dimensional Gaussian Process Regression,” IEEE Access, vol. 10, no. January 2022, doi: 10.1109/ACCESS.2022.3217912.
[15]W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, NUMERICAL RECIPES: The Art of Scientific Computing. Cambridege University Press, 2007.