Abstract
The paper evaluates the performance of Focused Time Delay, Distributed Time Delay (DTD), Layer Recurrent, and Nonlinear Autoregressive dynamic neural networks for estimating path loss of mobile radio signals, by training a semi empirical model. The path losses predicted with Walfisch Bertoni, Walfisch-Ikegami (WI), Sakagami and Xia models are compared with the path loss extracted from measured mobile signal strengths at frequency of 947.5 MHz in Hyderabad city of India. The best suited, Walfisch-Ikegami model is trained with feedback neural networks using Levenberg Marquardt, Scale Conjugate Gradient and Resilient Propagation training algorithms. The DTD neural network, trained by Levenberg algorithm has good performance with MSE (3.33) and correlation (0.987). The highlight is the proposed Hybrid-Neural Network Walfisch-Ikegami (H-NNWI) model which implements DTD neural network with a modified Walfisch-Ikegami model. The results prove the efficient performance of proposed model with least MSE (2.73), highest correlation (0.989) and improved path loss estimation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Saunders S, Aragon-Zavala A (2007) Antennas and propagation for wireless communication systems. Wiley, Hoboken
Lasisi H (2017) Development of a propagation path loss prediction model for mobile communication networks deployment in Osogbo, Nigeria. Eur J Eng Res Sci 2(11):13–17
Gschwendtner BE, Landstorfer FM (1995) Adaptive propagation modeling using hybrid neural technique. Electron Lett 32(3):162–164
Yuen CW, Wong WK, Qian SQ, Chan LK (2009) Fung EHK (2009) A hybrid model using genetic algorithm and neural network for classifying garment defects. Expert Syst Appl 36(2):2037–2047
Cavalcanti BJ, Cavalcante GA, de Mendonça LM, Cantanhede GM, de Oliveira MMM, D’Assunção AG (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. J Microwaves Optoelectron Electromagn Appl 16(3):708–722
Xia HH (1997) A simplified analytical model for predicting path loss in urban and suburban environments. IEEE Trans Veh Technol 46(4):1040–1046
Bhuvaneshwari A, Hemalatha R, Satyasavithri T (2013) Development of an empirical power model and path loss investigations for dense urban region in Southern India. In: 2013 IEEE Malaysia international conference on communications (MICC). IEEE, pp. 500–505
Chiang Y-M, Chang L-C, Chang F-J (2004) Comparison of static-feed forward and dynamic-feedback neural networks for rainfall–runoff modeling. J Hydrol 290(3–4):297–311
Bhuvaneshwari A, Hemalatha R, Satyasavithri T (2016) Performance evaluation of Dynamic Neural Networks for mobile radio path loss prediction. In: 2016 IEEE Uttar Pradesh section international conference on electrical, computer and electronics engineering (UPCON). IEEE
Giles CL, Kuhn GM, Williams RJ (1994) Dynamic recurrent neural networks: theory and applications. IEEE Trans Neural Netw 5:153–156
Diaconescu E (2008) The use of NARX neural networks to predict chaotic time series. Wseas Trans Comput Res 3(3):182–191
Baghirli O (2015) Comparison of Lavenberg-Marquardt scaled conjugate gradient and Bayesian regularization back propagation algorithms for multistep ahead wind speed forecasting using multilayer perceptron feed forward neural network. Master of Science with a Major in Energy Technology with Focus on Wind Power, Department of Earth Sciences, Uppsala University
Popescu I, Nafomita P, Constantinou P, Kanatas A, Moraitis N (2001) Neural networks applications for the prediction of propagation path loss in urban environments. In: 2001 IEEE VTS 53rd vehicular technology conference, spring proceedings, Rhodes, Greece, vol 1, pp 387–391
Ambroziak SJ, Katulski RJ (2014) Statistical tuning of Walfisch-Ikegami model for the untypical environment. In: 2014 8th European conference on antennas and propagation. IEEE, pp 2087–2091
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Achayalingam, B., Rallapalli, H., Tirumala, S.S. (2020). Dynamic Neural Networks with Semi Empirical Model for Mobile Radio Path Loss Estimation. In: Satapathy, S.C., Raju, K.S., Shyamala, K., Krishna, D.R., Favorskaya, M.N. (eds) Advances in Decision Sciences, Image Processing, Security and Computer Vision. ICETE 2019. Learning and Analytics in Intelligent Systems, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-030-24318-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-24318-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24317-3
Online ISBN: 978-3-030-24318-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)