Characterization of Path Loss in the VHF Band using Neural Network Modeling Technique

Artificial Neural Networks (ANNs) which are one of the main tools used in machine learning have often been utilised in developing models for path loss modelling in recent times. However, the ANN algorithm that provides the best results has not been well established neither has the models been characterized to limit their performances and applications in the various frequency bands. In this paper, we characterize the propagation loss in the Very High Frequency Band (VHF, 30-300MHz) by using different ANN learning algorithms and activation functions based on the measurement data collected at 203.25 MHz in an urban environment (Ilorin, Nigeria). Prediction results of Hata, ECC-33, Egli and COST 231 propagation models at varying distances were fed into a feed-forward neural network and mapped to each corresponding measured path loss value. Statistical analysis shows that the ANN model that was trained with hyperbolic tangent activation function (HTAF), Levenberg-Marquardt (LM) algorithm, and 80 neurons in the hidden layer produced the most satisfactory results with Mean Error (ME), Root Mean Square Error (RMSE), Standard Deviation (SD), and coefficient of determination (R^2) values of 3.75 dB, 5.10 dB, 3.46 dB, and 0.95. However, the HTAF with Scale Conjugate Gradient (SCG) is more stable even though its prediction errors were slightly higher than that of LM.

[1]  V. S. Abhayawardhana,et al.  Comparison of empirical propagation path loss models for fixed wireless access systems , 2005, 2005 IEEE 61st Vehicular Technology Conference.

[2]  Aderemi A. Atayero,et al.  Comparative assessment of data obtained using empirical models for path loss predictions in a university campus environment , 2018, Data in brief.

[3]  Nasir Faruk,et al.  Improved path-loss model for predicting TV coverage for secondary access , 2014, Int. J. Wirel. Mob. Comput..

[4]  Katherine Siakavara,et al.  Mobile radio propagation path loss prediction using Artificial Neural Networks with optimal input information for urban environments , 2015 .

[5]  Elmer P. Dadios,et al.  Neural network-based path loss prediction for digital TV macrocells , 2015, 2015 International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management (HNICEM).

[6]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[7]  Aymen Ben Zineb,et al.  A Multi-wall and Multi-frequency Indoor Path Loss Prediction Model Using Artificial Neural Networks , 2016 .

[8]  Philip Constantinou,et al.  Neural networks applications for the prediction of propagation path loss in urban environments , 2001, IEEE VTS 53rd Vehicular Technology Conference, Spring 2001. Proceedings (Cat. No.01CH37202).

[9]  Hans-Jürgen Zepernick,et al.  Macrocell Path-Loss Prediction Using Artificial Neural Networks , 2010, IEEE Transactions on Vehicular Technology.

[10]  Rafael F. S. Caldeirinha,et al.  Modeling and inferring the attenuation induced by vegetation barriers at 2G/3G/4G cellular bands using Artificial Neural Networks , 2017 .

[11]  K. Siakavara,et al.  Application of a Composite Differential Evolution Algorithm in Optimal Neural Network Design for Propagation Path-Loss Prediction in Mobile Communication Systems , 2013, IEEE Antennas and Wireless Propagation Letters.

[12]  Namig J. Guliyev,et al.  A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function , 2015, Neural Computation.

[13]  J. N. Sahalos,et al.  Optimal Artificial Neural Network design for propagation path-loss prediction using adaptive evolutionary algorithms , 2013, 2013 7th European Conference on Antennas and Propagation (EuCAP).

[14]  Fang Dong,et al.  Fading channel modelling using single-hidden layer feedforward neural networks , 2017, Multidimens. Syst. Signal Process..

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

[16]  O. F. Oseni,et al.  Empirical Path Loss Models for GSM Network Deployment in Makurdi , Nigeria , 2014 .

[17]  Hojjat Adeli,et al.  An adaptive conjugate gradient learning algorithm for efficient training of neural networks , 1994 .

[18]  Segun Isaiah Popoola,et al.  Performance Evaluation of Radio Propagation Models on GSM Network in Urban Area of Lagos, Nigeria , 2014 .

[19]  Philip Constantinou,et al.  Comparison of neural network models for path loss prediction , 2005, WiMob'2005), IEEE International Conference on Wireless And Mobile Computing, Networking And Communications, 2005..

[20]  D. M. W. Powers,et al.  ROC-ConCert: ROC-Based Measurement of Consistency and Certainty , 2012, 2012 Spring Congress on Engineering and Technology.

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

[22]  Abiodun Musa Aibinu,et al.  Comparative Analysis of Basic Models and Artificial Neural Network Based Model for Path Loss Prediction , 2017 .

[23]  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).

[24]  Nadir Hakem,et al.  Neural Networks Model of an UWB Channel Path Loss in a Mine Environment , 2012, 2012 IEEE 75th Vehicular Technology Conference (VTC Spring).

[25]  Nasir Faruk,et al.  Error bounds of empirical path loss models at VHF/UHF bands in Kwara State, Nigeria , 2013, Eurocon 2013.

[26]  Nasir Faruk,et al.  On the Study of Empirical Path Loss Models for Accurate Prediction of Tv Signal for Secondary Users , 2013 .

[27]  G. Cerri,et al.  Feed forward neural networks for path loss prediction in urban environment , 2004, IEEE Transactions on Antennas and Propagation.

[28]  N. Hakem,et al.  Comparative experimental study on modeling the path loss of an UWB channel in a mine environment using MLP and RBF neural networks , 2012, 2012 International Conference on Wireless Communications in Underground and Confined Areas.

[29]  Francesco Rinaldi,et al.  Path loss prediction in urban environment using learning machines and dimensionality reduction techniques , 2009, Comput. Manag. Sci..

[30]  Abiodun Musa Aibinu,et al.  Artificial Neural Network model for the determination of GSM Rxlevel from atmospheric parameters , 2017 .

[31]  A. Bhuvaneshwari,et al.  Performance evaluation of Dynamic Neural Networks for mobile radio path loss prediction , 2016, 2016 IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering (UPCON).

[32]  J. D. Parsons,et al.  The Mobile Radio Propagation Channel , 1991 .

[33]  Ignacio Fernandez Anitzine,et al.  Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions , 2012 .

[34]  Joao M. M. Silva,et al.  Improvement of Outdoor Signal Strength Prediction in UHF Band by Artificial Neural Network , 2016, IEEE Transactions on Antennas and Propagation.

[35]  B. L. Kalman,et al.  Why tanh: choosing a sigmoidal function , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[36]  A. Atayero,et al.  Optimal model for path loss predictions using feed-forward neural networks , 2018 .