# Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

## Abstract

**:**

## 1. Introduction

## 2. Related Studies

## 3. Path Loss Prediction Models

#### 3.1. Deterministic Models

#### 3.2. Empirical Models

#### 3.2.1. Indoor Empirical Models

#### 3.2.2. The Log-Distance Path Loss Model

#### 3.2.3. The ITU Indoor Path Loss Model

## 4. Dataset Generation and Formulation

## 5. Path Loss Modeling Methods Based on ML

#### 5.1. Neural Network

#### 5.1.1. Loss Functions

#### 5.1.2. Activation Functions

#### 5.2. Random Forest

Algorithm 1: Random Forest. |

#### 5.3. Decision Tree

#### 5.4. Gradient Boosting

#### 5.5. Lasso Regression

## 6. Results

## 7. Conclusions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Aldossari, S.; Chen, K. Relay selection for 5g new radio via artificial neural networks. In Proceedings of the 22nd International Symposium On Wireless Personal Multimedia Communications (WPMC), Lisbon, Portugal, 24–27 November 2019; pp. 1–6. [Google Scholar]
- Hervis Santana, Y.; Martinez Alonso, R.; Guillen Nieto, G.; Martens, L.; Joseph, W.; Plets, D. Indoor Genetic Algorithm-Based 5G Network Planning Using a Machine Learning Model for Path Loss Estimation. Appl. Sci.
**2022**, 12, 3923. [Google Scholar] [CrossRef] - Barclay, L. Propagation of Radiowaves; IET: London, UK, 2003. [Google Scholar]
- Seybold, J. Introduction to RF Propagation; John Wiley & Sons: Hoboken, NJ, USA, 2005. [Google Scholar]
- Aldossari, S.; Chen, K. Predicting the Path Loss of Wireless Channel Models Using Machine Learning Techniques in MmWave Urban Communications. In Proceedings of the 22nd International Symposium On Wireless Personal Multimedia Communications (WPMC), Lisbon, Portugal, 24–27 November 2019; pp. 1–5. [Google Scholar]
- Series, P. Propagation Data and Prediction Methods for the Planning of Short-Range Outdoor Radiocommunication Systems and Radio Local Area Networks in the Frequency Range 300 MHz to 100 GHz; Tech. Rep., ITU, Tech. Rep. ITU-R; Electronic Publication: Geneva, Switzerland, 2015. [Google Scholar]
- Series, P. Propagation Data and Prediction Methods for the Planning of Indoor Radiocommunication Systems and Radio Local Area Networks in the Frequency Range 300 MHz to 450 GHz; Electronic Publication: Geneva, Switzerland, 2019. [Google Scholar]
- Xing, Y.; Rappaport, T.; Ghosh, A. Millimeter wave and sub-THz indoor radio propagation channel measurements, models, and comparisons in an office environment. IEEE Commun. Lett.
**2021**, 25, 3151–3155. [Google Scholar] [CrossRef] - Maccartney, G.; Rappaport, T.; Sun, S.; Deng, S. Indoor office wideband millimeter-wave propagation measurements and channel models at 28 and 73 GHz for ultra-dense 5G wireless networks. IEEE Access
**2015**, 3, 2388–2424. [Google Scholar] [CrossRef] - Jin, W.; Kim, H.; Lee, H. A Novel Machine Learning Scheme for mmWave Path Loss Modeling for 5G Communications in Dense Urban Scenarios. Electronics
**2022**, 11, 1809. [Google Scholar] [CrossRef] - Ma, S.; Cheng, H.; Lee, H. A Practical Approach to Indoor Path Loss Modeling Based on Deep Learning. J. Comput. Sci. Eng.
**2021**, 15, 84–95. [Google Scholar] [CrossRef] - Guo, Y.; Liu, Y.; Li, S. Modeling and Simulation of Terahertz Indoor Wireless Channel Based on Radial Basis Function Neural Network. In Proceedings of the 2021 International Conference On Microwave And Millimeter Wave Technology (ICMMT), Nanjing, China, 23–26 May 2021; pp. 1–3. [Google Scholar]
- Kim, H.; Jin, W.; Lee, H. mmWave path loss modeling for urban scenarios based on 3D-convolutional neural networks. In Proceedings of the 2022 International Conference on Information Networking (ICOIN), Jeju-si, Republic of Korea, 12–15 January 2022; pp. 441–445. [Google Scholar]
- Sani, U.; Malik, O.; Lai, D. Improving Path Loss Prediction Using Environmental Feature Extraction from Satellite Images: Hand-Crafted vs. Convolutional Neural Network. Appl. Sci.
**2022**, 12, 7685. [Google Scholar] [CrossRef] - Sotiroudis, S.; Siakavara, K.; Koudouridis, G.; Sarigiannidis, P.; Goudos, S. Enhancing machine learning models for path loss prediction using image texture techniques. IEEE Antennas Wirel. Propag. Lett.
**2021**, 20, 1443–1447. [Google Scholar] [CrossRef] - Igwe, K.; Oyedum, O.; Aibinu, A.; Ajewole, M.; Moses, A. Application of artificial neural network modeling techniques to signal strength computation. Heliyon
**2021**, 7, e06047. [Google Scholar] [CrossRef] [PubMed] - Preusser, K.; Schmeink, A. Robust Channel Modeling of 2.4 GHz and 5 GHz Indoor Measurements: Empirical, Ray Tracing, and Artificial Neural Network Models. IEEE Trans. Antennas Propag.
**2021**, 70, 559–572. [Google Scholar] [CrossRef] - Piacentini, M.; Rinaldi, F. Path loss prediction in urban environment using learning machines and dimensionality reduction techniques. Comput. Manag. Sci.
**2011**, 8, 371–385. [Google Scholar] [CrossRef] - Lotti, M.; Caillet, M.; D’Errico, R. Comparison of Indoor Channel Characteristics for Sub-THz Bands from 125 GHz to 300 GHz. In Proceedings of the 2022 16th European Conference On Antennas And Propagation (EuCAP), Madrid, Spain, 27 March–1 April 2022; pp. 1–5. [Google Scholar]
- Bal, M.; Marey, A.; Ates, H.; Baykas, T.; Gunturk, B. Regression of large-scale path loss parameters using deep neural networks. IEEE Antennas Wirel. Propag. Lett.
**2022**, 21, 1562–1566. [Google Scholar] [CrossRef] - Afroze, Z.; Matolak, D.; Dye, H. Indoor and Outdoor 90 GHz LOS-to-NLOS Channel Transition Characteristics. In Proceedings of the 2022 IEEE Wireless Communications And Networking Conference (WCNC), Austin, TX, USA, 10–13 April 2022; pp. 938–943. [Google Scholar]
- Omae, M.; Ndungu, E.; Kibet, P.; Tarus, H. Artificial intelligence approach to signal propagation modeling for outdoor to indoor wireless communication networks; a proposed study. In Proceedings of the Sustainable Research And Innovation Conference, Madrid, Spain, 19–21 November 2012; pp. 289–299. [Google Scholar]
- He, D.; Ai, B.; Guan, K.; Wang, L.; Zhong, Z.; Kürner, T. The design and applications of high-performance ray-tracing simulation platform for 5G and beyond wireless communications: A tutorial. IEEE Commun. Surv. Tutor.
**2018**, 21, 10–27. [Google Scholar] [CrossRef] - Teh, C.; Chung, B.; Lim, E. An accurate and efficient 3-D shooting-and-bouncing-polygon ray tracer for radio propagation modeling. IEEE Trans. Antennas Propag.
**2018**, 66, 7244–7254. [Google Scholar] [CrossRef] - Yun, Z.; Iskander, M. Ray tracing for radio propagation modeling: Principles and applications. IEEE Access
**2015**, 3, 1089–1100. [Google Scholar] [CrossRef] - Sun, S.; Rappaport, T.; Thomas, T.; Ghosh, A.; Nguyen, H.; Kovacs, I.; Rodriguez, I.; Koymen, O.; Partyka, A. Investigation of prediction accuracy, sensitivity, and parameter stability of large-scale propagation path loss models for 5G wireless communications. IEEE Trans. Veh. Technol.
**2016**, 65, 2843–2860. [Google Scholar] [CrossRef] - Das, S.S.; Prasad, R. Evolution of Air Interface Towards 5G: Radio Access Technology and Performance Analysis; River Publishers Series in Communications; CRC Press: Boca Raton, FL, USA, 2019. [Google Scholar]
- Zhang, P.; Yi, C.; Yang, B.; Wang, C.; Wang, H.; You, X. In-building coverage of millimeter-wave wireless networks from channel measurement and modeling perspectives. Sci. China Inf. Sci.
**2020**, 63, 1–16. [Google Scholar] [CrossRef] - Sun, S.; Rappaport, T.; Rangan, S.; Thomas, T.; Ghosh, A.; Kovacs, I.; Rodriguez, I.; Koymen, O.; Partyka, A.; Jarvelainen, J. Propagation Path Loss Models for 5G Urban Micro- and Macro-Cellular Scenarios. In Proceedings of the 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring), Nanjing, China, 15–18 May 2016; pp. 1–6. [Google Scholar]
- Dai, H.; Wong, R.; Wang, H.; Zheng, Z.; Vasilakos, A. Big Data Analytics for Large-scale Wireless Networks. ACM Comput. Surv.
**2019**, 52, 1–36. [Google Scholar] [CrossRef] [Green Version] - Liaw, A.; Wiener, M. Classification and regression by randomForest. R News
**2002**, 2, 18–22. [Google Scholar] - Aldosary, A.; Aldossari, S.; Chen, K.; Mohamed, E.; Al-Saman, A. Predictive wireless channel modeling of mmwave bands using machine learning. Electronics
**2021**, 10, 3114. [Google Scholar] [CrossRef] - Moreta, C.; Acosta, M.; Koo, I. Prediction of Digital Terrestrial Television Coverage Using Machine Learning Regression. IEEE Trans. Broadcast.
**2019**, 65, 702–712. [Google Scholar] [CrossRef] - Genuer, R.; Poggi, J. Random forests. Random For.
**2020**, 3, 33–55. [Google Scholar] - Famoriji, O.; Shongwe, T. Path Loss Prediction in Tropical Regions using Machine Learning Techniques: A Case Study. Electronics
**2022**, 11, 2711. [Google Scholar] [CrossRef] - Friedman, J.; Hastie, T.; Tibshirani, R. The Elements of Statistical Learning; Springer Series in Statistics New York; Springer: New York, NY, USA, 2001. [Google Scholar]
- Wilcox, K. An Introduction to Ensemble Methods for Machine Learning; Rochester Institute of Technology: Rochester, NY, USA, 2016. [Google Scholar]
- Suthaharan, S. Decision tree learning. In Machine Learning Models and Algorithms for Big Data Classification; Springer: Boston, MA, USA, 2016; pp. 237–269. [Google Scholar]
- Chai, T.; Draxler, R. Root mean square error (RMSE) or mean absolute error (MAE)–Arguments against avoiding RMSE in the literature. Geosci. Model Dev.
**2014**, 7, 1247–1250. [Google Scholar] [CrossRef] [Green Version] - Elmezughi, M.; Salih, O.; Afullo, T.; Duffy, K. Comparative analysis of major machine-learning-based path loss models for enclosed indoor channels. Sensors
**2022**, 22, 4967. [Google Scholar] [CrossRef] - Aldossari, S.; Chen, K. System and Method for Predicting Wireless Channel Path Loss. U.S. Patent 11,128,391, 21 September 2021. [Google Scholar]

ML Models | RMSE | MSE | MAE | R Square |
---|---|---|---|---|

Random Forest | 0.15 | 0.023 | 0.087 | 0.974 |

Decision Tree | 0.278 | 0.073 | 0.124 | 0.917 |

Lasso Regression | 0.192 | 0.037 | 0.162 | 0.957 |

Gradient Boosting | 0.161 | 0.026 | 0.084 | 0.970 |

Neural Network—Deep Learning | 0.234 | 0.054 | 0.182 | 0.938 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Aldossari, S.A.
Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band. *Electronics* **2023**, *12*, 497.
https://doi.org/10.3390/electronics12030497

**AMA Style**

Aldossari SA.
Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band. *Electronics*. 2023; 12(3):497.
https://doi.org/10.3390/electronics12030497

**Chicago/Turabian Style**

Aldossari, Saud Alhajaj.
2023. "Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band" *Electronics* 12, no. 3: 497.
https://doi.org/10.3390/electronics12030497