Investigation and Comparison of Generalization Ability of Multi-Layer Perceptron and Radial Basis Function Artificial Neural Networks for Signal Power Loss Prediction
This research work investigates, compares and presents three different approaches to avoid poor generalization and to overcome the tendencies of over-fitting in Radial Basis Function (RBF) and Multi-Layer Perceptron (MLP) artificial neural networks, in order to enhance the prediction accuracy of signal power loss during electromagnetic signal propagation in metropolitan area using measured data from a Long-Term Evolution (LTE) network. These approaches are a variation of hidden layer neurons, early stopping and Bayesian Regularization techniques. In the variation of the hidden layer neurons in MLP network, an excellent prediction has been recorded with 40 neurons while an increase in the number of neurons leads to poor network generalization. The network shows the capability of modeling a moderate size propagation network and, for more complex networks, intermediary layers or network modifications are required. For RBF network, the generalization ability of the network increases as the network gets more complex with 70 neurons in the hidden layer giving the best prediction. Training RBF network using early stopping approach gives a better prediction with less errors compared to neuron variation in the hidden layer and Bayesian Regularization in MLP network. However, in RBF network training, there is no difference in the errors obtained when early stopping approach has been used compared to Bayesian Regularization approach. It models appropriately a complex network without signs of over-fitting, and because of its fixed three-layer architecture, there is no poor generalization resulting from architectural complexity which Bayesian regularization approach tackles.
Copyright © 2019 Praise Worthy Prize - All rights reserved.
Virginia C. Ebhota, Joseph Isabona and Viranjay M. Srivastava, Base line knowledge on propagation modelling and prediction techniques in wireless communication networks, J. of Engineering and Applied Sciences (JEAS), vol. 13, no. 7, pp. 1919-1934, 2018.
S. Huang and K. K. Tan, Fault detection and diagnosis based on modeling and estimation methods, IEEE Trans. on Neural Networks, vol. 20, pp. 872-881, 2009.
O. Linda and M. Manic, Online spatio-temporal risk assessment for intelligent transportation systems, IEEE Trans. on Intelligent Transportation Systems, vol. 12, pp. 194-200, 2011.
B. J. Cavalcanti and G. A. Cavalcante, 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, vol. 16, pp. 704-718, 2017.
E. I. Udogu, Nigeria in the twenty-first century: strategies for political stability and peaceful co-existence, 1st ed. Trenton, New Jersey: Africa World Press, 2005.
C. S. Kumar Dash, A. Kumar Behera, S. Dehuri, and S.-B. Cho, Radial basis function neural networks: A topical state-of-the-art survey, Open Computer Science, vol. 6, pp. 33-63, 2016.
Tin-Yau Kwok and Dit-Yan Yeung, Constructive algorithms for structure learning in feedforward neural networks for regression problems, IEEE Transactions on Neural Networks, vol. 8, no. 3, pp. 630-645, May 1997.
O. U. Anyama and C. P. Igiri, An application of linear regression & artificial neural network model in the NFL result prediction, International Journal of Engineering Research & Technology vol. 4, pp. 457-461, 2015.
J. Isabona and Viranjay M. Srivastava, Hybrid neural network approach for predicting signal propagation loss in urban microcells networks, International Journal of Applied Engineering Research, vol. 11, pp. 11002-11008, 2016.
[H. Memarian and S. K. Balasundram, Comparison between multi-layer perceptron and radial basis function networks for sediment load estimation in a tropical watershed, Journal of Water Resource and Protection pp. 870-876, 2012.
K. Murat, Predictive abilities of Bayesian regularization and Levenberg–Marquardt algorithms in artificial neural networks: Acomparative empirical study on social data, Mathematical and Computational Applications, vol. 21, 2016.
T. Rajaee, S. A. Mirbagheri, M. Zounemat-Kermani, and V. Nourani, Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models, Science of the Total Environment, vol. 407, pp. 4916-4927, 2009.
A. Singh, M. Imtiyaz, R. K. Isaacc, and D. M. Denisc, Comparison of soil and water assessment tool (SWAT) and multilayer perceptron (MLP) Artificial Neural Network for predicting sediment yield in the nagwa agricultural watershed in Jharkhand, India, Agricultural Water Management, vol. 104, pp. 113-120, 2012.
J. Isabona and Viranjay M. Srivastava, Hybrid neural network approach for predicting signal propagation loss in urban microcells, IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Agra, India, 2016.
H. Anysz, A. Zbiciak, and N. Ibadova, The influence of input data standardization method on prediction accuracy of artificial neural networks, Procedia Engineering, vol. 153, pp. 66 - 70, 2016.
R. D. De Veaux and L. G. Ungar. (2017, 20/04). A brief introduction to neural networks. Available at: http://www.cis.upenn.edu/~ungar/Datamining/Publications/nnet-intro.pdf.
C. A. Deme, A generalized regression neural network model for path loss prediction at 900 MHZ for Jos city, Nigeria, American Journal of Engineering Research, vol. 5, pp. 1-7, 2016.
F. D. Foresee and M. T. Hagan, Gauss-Newton approximation to Bayesian learning, IEEE International Conference on Neural Networks, pp. 1930-1935, 1997.
R. J. Hyndman and A. B. Koehler, Another look at measures of forecast accuracy," International Journal of Forecasting, vol. 22, pp. 679-688, 2006.
C. J. Willmott and K. Matsuura, Advantages of the mean absolute error over the root mean square error in assessing average model performance, Climate Research, vol. 30, pp. 79-82, 2005.
[S. Ghahramani, Fundamentals of probability, 2nd Ed. New Jersey: Prentice Hall, 2000.
A. Buda and A. Jarynowski, Life time of correlations and its applications, Wydawnictwo Niezależne, pp. 5-21, 2010.
Rusilawati, R., Soeprijanto, A., Wibowo, R., Reactualization of a Modified Single Machine to Infinite Bus Model to Multimachine System Steady State Stability Analysis Studies Using Losses Network Concepts and Radial Basis Function Neural Network (RBFNN), (2017) International Review on Modelling and Simulations (IREMOS), 10 (2), pp. 112-120.
Hacib, T., Mekideche, M., Ferkha, N., Application of RBF Neural Network and Finite Element Analysis to Solve the Inverse Problem of Defect Identification, (2016) International Review of Physics (IREPHY), 10 (4), pp. 110-117.
Kerdphol, T., Qudaih, Y., Hongesombut, K., Watanabe, M., Mitani, Y., Intelligent Determination of a Battery Energy Storage System Size and Location Based on RBF Neural Networks for Microgrids, (2016) International Review of Electrical Engineering (IREE), 11 (1), pp. 78-87.
Triqui, B., Benyettou, A., Comparative Study Between Radial Basis Function and Temporal Neuron Network Basic in Cardiac Arrhythmia, (2018) International Journal on Communications Antenna and Propagation (IRECAP), 8 (2), pp. 186-193.
Hannane, A., Fizazi, H., Metaheuristics and Neural Network for Satellite Images Classification, (2016) International Review of Aerospace Engineering (IREASE), 9 (4), pp. 107-113.
Aberkane, M., Benouzza, N., Bendiabdellah, A., Boudinar, A., Discrimination between Supply Unbalance and Stator Short-Circuit of an Induction Motor Using Neural Network, (2017) International Review of Automatic Control (IREACO), 10 (5), pp. 451-460.
Si Tayeb, M., Fizazi, H., A Dual-Level Hybrid Approach for Classification of Satellite Images, (2017) International Review of Aerospace Engineering (IREASE), 10 (1), pp. 42-49.
- There are currently no refbacks.
Please send any question about this web site to email@example.com
Copyright © 2005-2020 Praise Worthy Prize