volume | PIER Journals

Abstract

Predicting signal power loss between the transmitter and receiver with minimal error is an important issue in telecommunication network planning and optimization process. In recent years, median order statistic filters have been exploited as a preprocessing constituent for analyzing signals. This work presents a resourceful predictive model, built on multi-layer perceptron (MLP) network with vector order statistic filter based preprocessing technique for improved prediction of measured signal power loss in a microcellular LTE network environment. The predictive model is termed Vector statistic filters multilayer perceptron (VSF-MLP). In terms of some essential performance evaluation indices such as the correlation coefficient, root-mean-square error and coefficient of efficiency, results show that VSF-MLP model prediction performs considerably better than the standard MLP model prediction approach on signal power data collected from different study locations in typical urban terrain.

1. Nouir, Z., B. Sayrac, B. Fourestie, and R. Nasri, "Enhancement of network planning tool predictions through measurements," IEEE 63rd Vehicular Technology Conference, 1117-1121, Melbourne, Vic., DOI: 10.1109/VETECS.2006.1683008, 2006. Google Scholar

2. Isabona, J. and V. M. Srivastava, "Hybrid neural network approach for predicting signal propagation loss in urban microcells," IEEE Region 10 Humanitarian Technology Conference (R10-HTC), 1-5, Agra, India, DOI: 10.1109/R10-HTC.2016.7906853, 2016. Google Scholar

3. Ostlin, E., H. J. Zepernick, and H. Suzuki, "Macro-cell path-loss prediction using Artificial Neural Networks," IEEE Transactions on Vehicular Technology, Vol. 59, No. 6, 2735-2747, DOI:10.1109/TVT.2010.2050502, Jul. 2010.
doi:10.1109/TVT.2010.2050502 Google Scholar

4. Han, P., X. J. Mao, S. M. Jiao, H. R. Sun, and L. H. Zhou, "Adaptive neural network control for drum water level based on fuzzy Self-Tuning," 2006 International Conference on Machine Learning and Cybernetics, 314-318, Dalian, China, 2006. Google Scholar

5. Andrea, N., C. Cecchetti, and A. Lipparwi, "Fast prediction of performance of wireless links by simulation trained neural networks," Proceeding of IEEE MTT-S Digest 2000, 429-432, 2000. Google Scholar

6. Peng, H. and S. Zhu, "Handling of incomplete data sets using ICA and SOM in data mining," Neural Computing & Applications, Vol. 16, No. 2, 167-172, DOI:10.1016/0893-6080(88)90017-2, 2007.
doi:10.1007/s00521-006-0058-6 Google Scholar

7. Wang, S. H., "Application of self-organising maps for data mining with incomplete data sets," Neural Computing & Applications, Vol. 12, No. 1, 42-48, DOI:10.1016/S08936080(97), 2003.
doi:10.1007/s00521-003-0372-1 Google Scholar

8. Xu, S. and L. Chen, "Adaptive higher order neural networks," 2009 WRI Global Congress on Intelligent Systems, 26-30, Xiamen, DOI:10.4018/978-1-59904-897-0.ch014, 2009. Google Scholar

9. Isabona, J. and V. M. Srivastava, "Hybrid neural network approach for predicting signal propagation loss in urban microcells networks," International Journal of Applied Engineering Research, Vol. 11, No. 22, 11002-11008, DOI: 10.1109/R10-HTC.2016.7906853, 2016. Google Scholar

10. Sotiroudis, S. P., K. Siakavara, and J. N. Sahalos, "A neural network approach to the prediction of the propagation path-loss for mobile communications systems in urban environments," PIERS Proceedings, 162-166, Prague, Czech Republic, Aug. 27-30, 2007. Google Scholar

11. Neskovic, A., N. Neskovic, and D. Paunovic, "Indoor electric field level prediction model based on the artificial neural networks," IEEE Communications Letters, Vol. 4, No. 6, 190-192, DOI: 10.1109/4234.848409, 2000.
doi:10.1109/4234.848409 Google Scholar

12. Fraile, R., L. Rubio, and N. Cardona, "Application of RBF neural networks to the prediction of propagation loss over irregular terrain," Proc. IEEE 52th Vehicular Tech. Conf., Vol. 2, 878-884, DOI: 10.1109/VETECF.2000.887127, Fall 2000. Google Scholar

13. Fraile, R. and N. Cardona, "Fast neural network method for propagation loss prediction in urban environments," Electronics Letters, Vol. 33, No. 24, 2056-2058, DOI: 10.1049/el: 19971378, 1997.
doi:10.1049/el:19971378 Google Scholar

14. Lee, W. H. and A. K. Y. Lai, "Function-based and physics-based hybrid modular neural network for radio wave propagation modeling," IEEE Antennas and Propagation Society International Symposium. C, 446-449, Salt Lake City, UT, USA, DOI: 10.1109/APS.2000.873858, 2000. Google Scholar

15. Venkata Ramana, R., B. Krishna, S. R. Kumar, and N. G. Pandey, "Monthly rainfall prediction using wavelet neural networks analysis," International Journal of Water Resources Management, Vol. 27, 3696-3711, DOI 10.1007/s11269-013-0374-4, 2013. Google Scholar

16. Zhang, M., S. Xu, and J. Fulcher, "Neuron-adaptive higher order neural-network models for automated financial data modelling," IEEE Transactions on Neural Networks, Vol. 13, No. 1, 188-204, DOI: 1045-9227(02)00361-2, 2002.
doi:10.1109/72.977302 Google Scholar

17. Ramana, R. V., B. Krishna, S. R. Kumar, and N. G. Pandey, "Monthly rainfall prediction using wavelet neural network analysis," International Journal of Water Resource Management, Vol. 27, 3697-3711, DOI: 10.1007/s11269-013-0374-4, 2013. Google Scholar

18. Chou, C. C., "A threshold based wavelet denoising method for hydrological data modelling," International Journal of Water Resource Management, Vol. 25, 1809-1830, DOI: 10.1080/02626667.2017.1371849, 2011. Google Scholar

19. Adamowski, J. and K. Sun, "Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds," Journal of Hydrology, Vol. 390, No. 1-2, 85-91, DOI: 10.1016/j.jhydrol.2010.06.033, 2010.
doi:10.1016/j.jhydrol.2010.06.033 Google Scholar

20. Wu, D., J. Wang, and Y. Teng, "Prediction of under-groundwater levels using wavelet decompositions and transforms," Journal of Hydrology Engineering, Vol. 5, 34-39, 2004. Google Scholar

21. Ali, A., R. Ghazali, and M. Mat Deris, "The wavelet multilayer perception for the prediction of earthquake time series data," Proceedings of the 13th International Conference on Information Integration and Web-based Applications and Services, 138-143, Ho Chi Minh City, Vietnam, DOI: 10.1145/2095536.2095561, 2011. Google Scholar

22. Wu, C. L., K. W. Chau, and C. Fan, "Prediction of rainfall time series using modular artificial neural networks coupled with data preprocessing techniques," Journal of Hydrology, Vol. 389, No. 1-2, 146-167, DOI:10.1016/j.jhydrol..05.040, 2010.
doi:10.1016/j.jhydrol.2010.05.040 Google Scholar

23. Jia, X., B. De Brabandere, T. Tuytelaars, and L. V. Gool, "Dynamic filter networks," 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, 2016. Google Scholar

24. Jothiprakash, V. and A. S. Kote, "Improving the performance of data-driven techniques through data pre-processing for modelling daily reservoir inflow," Journal of Hydrol. Sci. J, Vol. 56, 168-186, DOI: 10.1080/02626667.2010.546358, 2011. Google Scholar

25. Vijayakumar, N. N. and B. Plale, "Prediction of missing events in sensor data streams using Kalman Filters," Proceedings of the 1st Int’l Workshop on Knowledge Discovery from Sensor Data, in conjunction with ACM 13th Int’l Conference on Knowledge Discovery and Data Mining, 1-9, Aug. 2007. Google Scholar

26. Dotche, K. A., F. Sekyere, and W. Banuenulmah, "LPC for Signal analysis in cellular network coverage," Open Access Library Journal, Vol. 3, No. e2759, 1-10, DO1: 10.4236/oalib.1102759, 2016. Google Scholar

27. Chen, W. and K. Chau, "Intelligent manipulation and calibration of parameters for hydrological models," Int. Journal on. Environ. Pollut, Vol. 28, 432-447, 2006.
doi:10.1504/IJEP.2006.011221 Google Scholar

28. Nawi, N. M., W. H. Atomi, and M. Z. Zehman, "The Effect of data preprocessing on optimized training of artificial neural Networks," Procedia Technology, Vol. 11, 32-39, 2013.
doi:10.1016/j.protcy.2013.12.159 Google Scholar

29. Anysz, H., A. Zbiciak, and Nabi Ibadova, "The influence of input data standardization method on prediction accuracy of artificial neural networks," Procedia Engineering, Vol. 153, 66-70, DOI: 10.1016/j.proeng.2016.08.081, 2016. Google Scholar

30. Tripathi, V. R., "Image denoising using non-linear filter," International Journal of Modern Engineering Research (IJMER), Vol. 2, No. 6, 4543-4546, 2012. Google Scholar

31. Kumar, N. R. and J. U. Kumar, "A spatial mean and median filter for noise removal in digital images," International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol. 4, No. 1, 246-253, DOI: 10.15662/ijareeie.2015.0401037, 2015.
doi:10.15662/ijareeie.2015.0401037 Google Scholar

32. Tukey, J. W., "Nonlinear (Nonsuperposable) methods for smoothing data," Proceedings of Congress Record EASCON, 673, Washington DC, Oct. 7-9, 1974. Google Scholar

33. Lukac, R., K. N. Plataniotis, and B. Smolka, "Generalized selection weighted vector filters," EURASIP Journal on Applied Signal Processing, Vol. 12, 1870-1885, 2004. Google Scholar

34. Ye, W. and Z. Liao, "Generalized correlativity of median filtering operator on signals," Open Journal of Discrete Mathematics, Vol. 2, 83-87, DOI: 10.4236/ojdm.2012.23015, 2015. Google Scholar

35. Bovik, A. C. and T. S. Huang, "A generalization of median filtering using linear combinations of order statistics," IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. 31, No. 6, 1342-1349, DOI:10.1109/TASSP.1983.1164247, 1983.
doi:10.1109/TASSP.1983.1164247 Google Scholar

36. Oten, R. and R. J. P. de Figueiredo, "An efficient method for L-filter design," IEEE Transactions on Signal Processing, Vol. 51, No. 1, 193-203, DOI: 10.1109/TSP.2002.806573, 2003.
doi:10.1109/TSP.2002.806573 Google Scholar

37. Marquardt, D., "An algorithm for least-squares estimation of nonlinear parameters," SIAM Journal on Applied Mathematics, Vol. 11, No. 2, 431-441, DIO:10.1137/0111030, 1963.
doi:10.1137/0111030 Google Scholar

Dr. Virginia Chika Ebhota

Dr. Joseph Isabona

Dr. Viranjay M. Srivastava