Radio Propagation Models Based on Machine Learning Using Geometric Parameters for a Mixed City-River Path

This work presents and evaluates the use of geometric parameters of the environment in the prediction of the electric field in mixed city-river type environments, employing two techniques of Machine Learning (ML) as Artificial Neural Networks (ANN) and Neuro-Fuzzy System (NFS). For its development, measurements were carried out in Amazon Region, Belém city, in the 521 MHz band. The input parameters for an ANN and NFS are the distance between transmitter and receiver, the distance only over the river, the height of the ground, the radius of the first Fresnel ellipsoid, and the electric field of free space. The ANN is a Multilayer Perceptron Network (MLP) that uses the Levenberg-Marquardt training algorithm and cross-validation method. The NFS is an Adaptive Neuro-Fuzzy Inference System (ANFIS) that uses the model Sugeno. The results obtained compared with the classic literature models (ITU-R 1546 and Okumura-Hata) in the city for distances up 20 km and over the river for distances up 5 km. A quantitative analysis is performed between the measured and predicted data through the Standard deviation (SD), Root Mean Square Error (RMSE), and the Grey Relational Grade, combined with the Mean Absolute Percentage Error (GRG-MAPE). For ANN, the SD is 2.13, the RMSE is 2.11 dB, and the GRG-MAPE is 0.96. Also, for the NFS, the SD is 1.99, the RMSE is 2.06 dB, and the GRG-MAPE is 0.97. It should be noted that the transition zone between the city and the river was characterized by the proposed ANN and NFS in contrast with the classic literature models, which did not demonstrate coherence in the transition zone.

[1]  Megha G. Mathpal.  A Landmark Based Shortest Path Detection by Using A* and Haversine Formula , 2018 .

[2]  Theodore S. Rappaport,et al.  Wireless Communications: Principles and Practice (2nd Edition) by , 2012 .

[3]  L. Correia,et al.  A Propagation Model for Mixed Paths Using Dyadic Green's Functions: A Case Study Over the River for a City–River–Forest Path , 2018, IEEE Antennas and Wireless Propagation Letters.

[4]  M. Hata,et al.  Empirical formula for propagation loss in land mobile radio services , 1980, IEEE Transactions on Vehicular Technology.

[5]  D. Barrick,et al.  Estimation of HF radar mixed-media path loss using the millington method , 2015, 2015 IEEE/OES Eleveth Current, Waves and Turbulence Measurement (CWTM).

[6]  G. Millington,et al.  Ground-wave propagation over an inhomogeneous smooth earth , 1949 .

[7]  Luís M. Correia,et al.  A Radio Propagation Model for Mixed Paths in Amazon Environments for the UHF Band , 2018, Wirel. Commun. Mob. Comput..

[8]  Kun Yang,et al.  GRG-MAPE and PCC-MAPE Based on Uncertainty-Mathematical Theory for Path-Loss Model Selection , 2016, 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring).

[10]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[11]  J. C. Reyes-Guerrero,et al.  5.8 GHz propagation of low-height wireless links in sea port scenario , 2014 .

[12]  Carlos T. Calafate,et al.  Path Loss Predictions in the VHF and UHF Bands Within Urban Environments: Experimental Investigation of Empirical, Heuristics and Geospatial Models , 2019, IEEE Access.

[13]  Diego K. N. da Silva,et al.  Radio propagation for the Amazon Region considering the river level , 2019, 2019 Workshop on Communication Networks and Power Systems (WCNPS).

[14]  S. Yoshida,et al.  Propagation factors controlling mean field strength on urban streets , 1984 .

[15]  G. P. S. Cavalcante,et al.  Methodologies for path loss prediction in LTE-1.8 GHz networks using neuro-fuzzy and ANN , 2017, 2017 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference (IMOC).

[16]  S. Tabbane,et al.  A UHF Path Loss Model Using Learning Machine for Heterogeneous Networks , 2017, IEEE Transactions on Antennas and Propagation.

[17]  Nasir Faruk,et al.  Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel , 2019, IEEE Access.

[18]  Tammam A. Benmus,et al.  Neural network approach to model the propagation path loss for great Tripoli area at 900, 1800, and 2100 MHz bands , 2015, 2015 16th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA).

[19]  L. Sevgi,et al.  FEM-Based Surface Wave Multimixed-Path Propagator and Path Loss Predictions , 2009, IEEE Antennas and Wireless Propagation Letters.

[20]  F. A. Pontes,et al.  Araraiana e Combu: um estudo comparativo de dois contextos ribeirinhos amazônicos , 2012 .

[21]  C. H. Slump,et al.  Mixed-path trans-horizon UHF measurements for P.1546 propagation model verification , 2011, 2011 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications.

[22]  Wei Chen,et al.  Path Loss Channel Model for Inland River Radio Propagation at 1.4 GHz , 2017 .

[23]  Juan Torres,et al.  Improved ITU-R model for digital terrestrial television propagation path loss prediction , 2017 .