• Bruno J. Cavalcanti,
  • Gustavo A. Cavalcante
  • Laércio M. de Mendonça
  • Gabriel M. Cantanhede
  • Marcelo M.M.de Oliveira
  • Adaildo G. D’Assunção




Artificial Neural Networks – ANN, Long Term Evolution – LTE, Long Term Evolution Advanced – LTE-A, propagation models, path loss


This article presents the development and analysis of a hybrid, error correction-based, neural network to predict the path loss for suburban areas at 800 MHz and 2600 MHz, obtained by combining empirical propagation models, ECC-33, Ericsson 9999, Okumura Hata, and 3GPP's TR 36.942, with a backpropagation Artificial Neural Network (ANN). The network performance was tested along with two optimization techniques - Genetic Algorithm (GA) and Least Mean Square (LMS). Results were compared with data obtained by measurements performed in the vicinity of the Federal University of Rio Grande do Norte (UFRN), in the city of Natal, Brazil. In the end, the hybrid neural network presented the best results, indicating greater similarity with experimental data. The results developed in this research will help to achieve better signal estimation, reducing errors in planning and implementation of LTE and LTE-A systems.


[1] N. Shabbir et al., “Comparison of Radio Propagation Models for Long Term Evolution (LTE) Network,” International Journal of NextGeneration Networks, vol. 3, no. 3, 2011.
[2] M. Rumney. LTE and the Evolution to 4G: Wireless Design and Measurement Challenges, 2nd ed. United Kingdom: John Wiley &
Sons Ltd., 2013.
[3] M. Ahmed, “Performance test of 4G (LTE) networks in Saudi Arabia,” in Proc. International Conference on Technological Advances
in Electrical, Electronics and Computer Engineering., Turkey, 2013, pp. 28-33.
[4] N. S. Nkordeh et al., “LTE Network Planning using the Hata-Okumura and the COST-231 Hata Pathloss Models” in World Congress
on Engineering., London., UK, 2014.
[5] Y. A. Ahmad et al., “Studying Different Propagation Models for LTE-A System,” in International Conference on Computer and
Communication Engineering., Malaysia, 2012, pp. 848–853.
[6] G.R. Pallardó, “On DVB-H Radio Frequency Planning: Adjustment of a Propagation Model Through Measurement Campaign
Results,” M.S. thesis, Dept of technology and Built Enviroment, University of Gävle, 2008.
[7] W. Chan, et al., "Listen, attend and spell: A neural network for large vocabulary conversational speech recognition", in Acoustics,
Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 2016. pp. 4960-4964.
[8] T. Wang et al., "A combined adaptive neural network and nonlinear model predictive control for multirate networked industrial
process control", in IEEE Transactions on Neural Networks and Learning Systems, v. 27, n. 2, 2016, pp. 416-425.
[9] W. Li et al., "Deepreid: Deep filter pairing neural network for person re-identification", in Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, 2014. pp. 152-159.
[10] F.G. Aguia, “Utilização de redes neurais artificais para detecção de padrões de vazamento em dutos,” Ph.D. dissertation in portuguese,
Federal University of São Paulo., São Carlos., SP, 2010.
[11] I. Popescu et al., “Comparison of neural network models for path loss prediction,” in IEEE International Conference on Wireless And
Mobile Computing, Networking And Communications., Montreal., QC, 2005, pp. 44–49.
[12] D. Wu et al., “Application of artificial neural networks for path loss prediction in railway environments”, in Communications and
Networking in China, 2010, pp. 1-5.
[13] E. Ostlin et al.,"Macrocell radio wave propagation prediction using an artificial neural network", in Vehicular Technology Conference,
2004. VTC2004-Fall. 2004 IEEE 60th vol.1, 2004, pp. 57-61.
[14] E. Ostlin et al., "Macrocell path-loss prediction using artificial neural networks", in IEEE Transactions on Vehicular Technology, v.
59, n. 6, 2010, pp. 2735-2747.
[15] C. D. Angeles and E. P. Dadios., “Neural network-based path loss prediction for digital TV macrocells,” in Humanoid,
Nanotechnology, Information Technology, Communication and Control, Environment and Management., Cebu., PH, 2015.
[16] I. Popescu et al., “Applications of generalized RBF-NN for path loss prediction,” Personal, Indoor and Mobile Radio Communications,
2002. The 13th IEEE International Symposium on, vol. 1, 2002, pp. 484-488.
[17] S. S. Kale and A. N. Jadhav, “Performance analysis of empirical propagation models for WiMAX in urban environment,” OSR J.
Electron. Commun. Engin, 2013.
[18] LTE; Evolved Universal Terrestrial Radio Access (E-UTRA); Physical channels and modulation (3GPP TS 36.211 version 8.7.0
Release 8), ETSI, 2009.
[19] J. Milanovic et al., “Comparison of propagation model accuracy for WiMAX on 3.5GHz” in 14th IEEE International conference on
electronic circuits and systems., Marrakech., MA, 2007.
[20] Electronic Communication Committee (ECC) within the European Conference of Postal and Telecommunications Administration,
(2003) May, "The Analysis of the Coexistence of FWA Cells in the 3.4-3.8 GHz Band," Tech. Rep., ECC Report 33.
[21] Google Maps, 2016. Map of UFRN campus. [online]. Google. Available from: https://goo.gl/maps/1RbPQwn5o6y [Accessed 24
November 2016].
[22] D. Marquardt, “An Algorithm for Least-squares Estimation of Nonlinear Parameters,” SIAM Journal Applied Mathematics, vol. 11,
1963, pp. 431–441.
[23] J. J. Moré, “The Levenberg-Marquardt Algorithm: Implementation and Theory,” Numerical Analysis, ed. G. A. Watson, Lecture Notes
in Mathematics 630, Berlin: Springer Verlag, 1977.
[24] Krogh et al, "Neural network ensembles, cross validation, and active learning," Advances in neural information processing systems 7,
1995, pp. 231-238.




How to Cite

Bruno J. Cavalcanti, Gustavo A. Cavalcante, Laércio M. de Mendonça, Gabriel M. Cantanhede, Marcelo M.M.de Oliveira, & Adaildo G. D’Assunção. (2017). A HYBRID PATH LOSS PREDICTION MODEL BASED ON ARTIFICIAL NEURAL NETWORKS USING EMPIRICAL MODELS FOR LTE AND LTE-A AT 800 MHZ AND 2600 MHZ. Journal of Microwaves, Optoelectronics and Electromagnetic Applications (JMOe), 16(3), 708–722. https://doi.org/10.1590/2179-10742017v16i3925



Regular Papers

Most read articles by the same author(s)