Wireless Personal Communications

, Volume 104, Issue 3, pp 935–948 | Cite as

Environment-Adaptation Based Hybrid Neural Network Predictor for Signal Propagation Loss Prediction in Cluttered and Open Urban Microcells

  • Virginia Chika Ebhota
  • Joseph IsabonaEmail author
  • Viranjay M. Srivastava


In the design and placement of radio base station transmitters, the accurate field signal power prediction and modelling is of critical importance. In this work, an adaptive neural network predictor which combines multilayer perception (MLP) and adaptive linear element (Adaline) is proposed for enhanced signal propagation loss prediction in microcellular urban environments. The prediction accuracy of the proposed Hybrid adaptive neural network predictor has been tested and evaluated using experimental field strength data acquired from LTE radio network environment with mixed residential, commercial and cluttered building structures. By means of first order statistical performance evaluation metrics, namely, regression coefficient (R), root mean squared error, standard deviation and mean absolute error, the proposed adaptive hybrid approach provide a better prediction accuracy compared to the standard MLP ANN prediction approach. The superior performance of the hybrid neural predictor can be attributed to its capability to learn, adaptively respond and predict the fluctuating patterns of the reference propagation loss data during training.


Signal power Signal coverage Signal prediction MLP prediction Adaptive Prediction 



  1. 1.
    Amaldi, E., Capone, A., & Malucelli, F. (2008). Radio planning and coverage optimization of 3G cellular networks. Wireless Networks, 14(4), 435–447.CrossRefGoogle Scholar
  2. 2.
    Isabona, J., & Srivastava, V. M. (2017). Coverage and link quality trends in suburban mobile broadband HSPA network environments. Wireless Personal Communications, 2017, 1–14.Google Scholar
  3. 3.
    Neskovic, A., & Neskovic, N. (2010). Microcell electric field strength prediction model based upon artificial neural networks. International Journal Electronics and Communication (AEU), 64, 733–738.CrossRefGoogle Scholar
  4. 4.
    Ostlin, E., Zepernick, H.-J., & Suzuki, H. (2010). Macrocell path loss prediction using artificial neural networks. IEEE Transactions on Vehicular Technology, 59(6), 2735–2747.CrossRefGoogle Scholar
  5. 5.
    Neskovic, A., Neskovic, N., & Paunovic, D. (2000). Indoor electric field level prediction model based on the artificial neural networks. IEEE Communication Letters, 4(6), 190–192.CrossRefGoogle Scholar
  6. 6.
    Popescu, I., Nikitopoulos, D., Constantinou, P., & Nafornita, I. (2006). ANN prediction models for outdoor environment. In Proceeding of 17th IEEE international symposium on personal, indoor, mobile radio communication, Helsinki, Finland.Google Scholar
  7. 7.
    Sharma, S., Kumar, V., & Kumar, R. (2012). Spervised online asaptive control of inverted pendulum system using ADALINE artificail neural networks with varying system parameters and external disturbance. International Journal of Interlligent Systems and Applications, 8, 53–61.CrossRefGoogle Scholar
  8. 8.
    Gao, X. M., Gao, X. Z., Tanskanen, J. M. A., & Ovaska, S. J. (1997). Power prediction in mobile communication systems using an optimal neural-network structure. IEEE Transactions on Neural Networks, 8(6), 1145–1455.CrossRefGoogle Scholar
  9. 9.
    Ardalani, N., Khoogar, A., & Roohi, H. (2007). A comparison of Adaline and MLP neural network based predictors in SIR estimation in mobile DS/CDMA systems, world academy of science, engineering and technology. International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, 1(9), 1382–1387.Google Scholar
  10. 10.
    Gschwendtner, B. E., & Landstorfer, F. M. (1996). Adaptive propagation modeling using a hybrid neural technique. Electronics Letters, 32(3), 162–164.CrossRefGoogle Scholar
  11. 11.
    Isabona, J., & Srivastava, V. M. (2016). Hybrid neural network approach for predicting signal propagation loss in urban microcells. In Proceeding of 2016 IEEE region 10 humanitarian technology conference (R10-HTC), Agra, India.Google Scholar
  12. 12.
    Isabona, J., & Srivastava, V. M. (2016). A neural network based model for signal coverage propagation loss prediction in urban radio communication environment. International Journal of Applied Engineering Research, 11(22), 11002–11008.Google Scholar
  13. 13.
    Yonaba, H., Anctil, F., & Fortin, V. (2010). Comparing sigmoid transfer functions for neural network multistep ahead streamflow forecasting. Journal of Hydrologic Engineering, 15(4), 275–283.CrossRefGoogle Scholar
  14. 14.
    Torre, A., Garcia, F., Moromi, I., Espinoza, P., & Acuna, L. (2015). Prediction of compression strength of high performance concrete using artificial neural networks. Journal of Physics: Conference Series, 582, 1–6.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Electronic Engineering, Howard CollegeUniversity of KwaZulu-NatalDurbanSouth Africa

Personalised recommendations