Echo state network-based radio signal strength prediction for wireless communication in Northern Namibia
- Author(s): Kenneth Gideon 1 ; Clement Nyirenda 1 ; Clement Temaneh-Nyah 1
-
-
View affiliations
-
Affiliations:
1:
Department of Electronics and Computer Engineering , University of Namibia , Windhoek , Namibia
-
Affiliations:
1:
Department of Electronics and Computer Engineering , University of Namibia , Windhoek , Namibia
- Source:
Volume 11, Issue 12,
24
August
2017,
p.
1920 – 1926
DOI: 10.1049/iet-com.2016.1290 , Print ISSN 1751-8628, Online ISSN 1751-8636
A method for predicting radio signal strength using echo state networks (ESNs) is proposed and applied to three different locations in Northern Namibia. This method aims at providing a better way for radio signal strength prediction, which leads to improvements in wireless communication planning, design and analysis. Its performance is compared with the support vector regression (SVR) method optimised for radio propagation modelling. Simulations are conducted in Python using propagation data measured from the three locations based on the following four performance measures: goodness of fit criteria; error measures; computation complexities; and F-test for statistical model comparison. Simulation results show that the ESN method gives a better prediction accuracy in terms of the goodness of fit criteria and the error measures; however, it is inferior to the SVR method in terms of computation complexities. In addition, results from the F-test also indicate that the ESN method provides a significantly better fit than the SVR method.
Inspec keywords: radio networks
Other keywords: radio propagation modelling; wireless communication planning; echo state network-based radio signal strength prediction; ESN method
Subjects: Radio links and equipment
References
-
-
1)
-
14. Azpilicueta, L., Rawat, M., Rawat, K.: ‘A ray launching-neural network approach for radio wave propagation analysis in complex indoor environments’, IEEE Trans. Antennas Propag., 2014, 62, (5), pp. 2777–2786.
-
-
2)
-
11. Oluwole, F.J., Olajide, O.Y.: ‘MATLAB graphical user interface (GUI) for wireless metropolitan area network optimum performance Okumura-Hata’, Int. J. Sci. Technol., 2013, 2, (6), pp. 429–432.
-
-
3)
-
44. Abdi, H., Williams, L.J.: ‘Tukey's honestly significant difference (HSD) test’, Encycl. Res. Des. Thousand Oaks, CA Sage, 2010, 1, pp. 1–5.
-
-
4)
-
28. Forney, E.M., Anderson, C.W., Gavin, W.J., et al: ‘Echo state networks for modeling and classification of EEG signals in mental-task brain-computer interfaces’, Fort Collins, 2015, pp. 1–23.
-
-
5)
-
12. Mom, J.M., Mgbe, C.O., Igwue, G.A.: ‘Application of artificial neural network for path loss prediction in urban macrocellular environment’, Am. J. Eng. Res., 2014, 3, (2), pp. 270–275.
-
-
6)
-
22. Jaeger, H.: ‘Echo state network’, Scholarpedia, 2007, 2, (9), p. 2330.
-
-
7)
-
9. Temaneh-Nyah, C., Nepembe, J.: ‘Determination of a suitable correction factor to a radio propagation model for cellular wireless network analysis’. 2014 5th Int. Conf. on Intelligent Systems, Modelling and Simulation, 2014, pp. 175–182.
-
-
8)
-
4. Lukoševičius, M.: ‘A practical guide to applying echo state networks’, in Montavon, G., Orr, G.B., Müller, K.-R. (Eds.): ‘Neural networks: tricks of the trade’ (Springer, Berlin Heidelberg, 2012, 2nd ed.), vol. 7700, pp. 659–686.
-
-
9)
-
34. Claesen, M., Simm, J., Popovic, D., et al: ‘Easy hyperparameter search using optunity’, arXiv Prepr. arXiv1412.1114, 2014, pp. 1–5.
-
-
10)
-
40. Kurz-Kim, J.-R., Loretan, M.: ‘On the properties of the coefficient of determination in regression models with infinite variance variables’, J. Econom., 2014, 181, (1), pp. 15–24.
-
-
11)
-
38. Bergstra, J., Yamins, D., Cox, D.: ‘Making a science of model search’, arXiv Prepr. arXiv1209.5111, 2012, pp. 1–11.
-
-
12)
-
21. Han, M., Xu, M.: ‘Predicting multivariate time series using subspace echo state network’, Neural Process. Lett., 2015, 41, (2), pp. 201–209.
-
-
13)
-
20. Lukoševičius, M., Jaeger, H., Schrauwen, B.: ‘Reservoir computing trends’, KI – Künstliche Intelligenz, 2012, 26, pp. 365–371.
-
-
14)
-
5. Timoteo, R.D.A., Cunha, D.C., Cavalcanti, G.D.C.: ‘A proposal for path loss prediction in urban environments using support vector regression’. Advanced Int. Conf. on Telecommunications, 2014, vol. 10, no. c, pp. 119–124.
-
-
15)
-
31. Pedregosa, F., Varoquaux, G., Gramfort, A., et al: ‘Scikit-learn: machine learning in python’, J. Mach. Learn. Res., 2012, 12, pp. 2825–2830.
-
-
16)
-
37. Bergstra, J., Bardenet, R., Bengio, Y., et al: ‘Algorithms for hyper-parameter optimization’, 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), 2011, pp. 2546–2554.
-
-
17)
-
33. Bergstra, J., Bengio, Y.: ‘Random search for hyper-parameter optimization’, J. Mach. Learn. Res., 2012, 13, pp. 281–305.
-
-
18)
-
17. Sotiroudis, S.P., Siakavara, K., Sahalos, J.N.: ‘A neural network approach to the prediction of the propagation path-loss for mobile communications systems in urban environments’, PIERS Online, 2007, 3, (8), pp. 1175–1179.
-
-
19)
-
25. Rabin, M.J.A., Hossain, M.S., Ahsan, M.S., et al: ‘Sensitivity learning oriented nonmonotonic multi reservoir echo state network for short-term load forecasting’. Int. Conf. on Informatics, Electronics Vision (ICIEV), 2013, 2013, pp. 1–6.
-
-
20)
-
26. Morando, S., Jemei, S., Gouriveau, R., et al: ‘Fuel cells remaining useful lifetime forecasting using echo state network’. Vehicle Power and Propulsion Conf. (VPPC), 2014 IEEE, 2014, pp. 1–6.
-
-
21)
-
24. Ho, J.: ‘The Wiener-Hopf method and its applications in fluids’ (The University of Melbourne Department, 2007).
-
-
22)
-
6. Smola, A.J., Sch, B., Schölkopf, B.: ‘A tutorial on support vector regression’, Stat. Comput., 2004, 14, (3), pp. 199–222.
-
-
23)
-
10. Radiocommunication Sector of ITU: ‘Rec. ITU-R P.1546-5: Method for point-to-area predictions for terrestrial services in the frequency range 30 MHz to 3000 MHz’, Geneva, 2013.
-
-
24)
-
23. Yu, P., Miao, L., Jia, G.: ‘Clustered complex echo state networks for traffic forecasting with prior knowledge’. Instrumentation and Measurement Technology Conf. (I2MTC), 2011 IEEE, 2011, pp. 1–5.
-
-
25)
-
19. Schmidhuber, J.: ‘Recurrent neural networks’, 2015. Available at http://people.idsia.ch/~juergen/rnn.html, Accessed 16 February 2016.
-
-
26)
-
1. Gupta, N.: ‘Introduction to wireless communication’, in Gupta, N. (Ed.): ‘Inside Bluetooth low energy’ (Artech House Mobile Communications, London, 2013).
-
-
27)
-
29. Fernández Anitzine, I., Romo Argota, J.A., Fontán, F.P.: ‘Influence of training set selection in artificial neural network-based propagation path loss predictions’, Int. J. Antennas Propag., 2012, 2012, pp. 1–7.
-
-
28)
-
8. Modi, V.: ‘Radio wave propagation’, IOSR J. Electron. Commun. Eng., 2014, 9, (1), pp. 17–19.
-
-
29)
-
27. Yusoff, M.-H., Chrol-Cannon, J., Jin, Y.: ‘Modeling neural plasticity in echo state networks for classification and regression’, Inf. Sci. (Ny)., 2016, 364, pp. 184–196.
-
-
30)
-
2. Ostlin, E., Zepernick, H.-J., Suzuki, H.: ‘Macrocell path-loss prediction using artificial neural networks’, IEEE Trans. Veh. Technol., 2010, 59, (6), pp. 2735–2747.
-
-
31)
-
16. Sarka, A., Majumdar, S., Bhattacharya, P.P.: ‘Path loss estimation for a wireless sensor network for application in ship’, Int. J. Comput. Sci. Mob. Comput., 2013, 2, (6), pp. 87–96.
-
-
32)
-
41. Peng, X., Xu, D., Kong, L., et al: ‘L1-norm loss based twin support vector machine for data recognition’, Inf. Sci. (Ny)., 2016, 340–341, pp. 86–103.
-
-
33)
-
35. Claesen, M., De Moor, B.L.R., Simm, J., et al: ‘Hyperparameter tuning in python using optunity’. Proc. of the Int. Workshop on Technical Computing for Machine Learning and Mathematical Engineering, 2014, pp. 6–7.
-
-
34)
-
43. Small, A.: ‘Scientific python for both expert and novice programmers’, Comput. Sci. Eng., 2012, 14, (2), pp. 6–7.
-
-
35)
-
15. Shi, K., Ma, Z., Zhang, R., et al: ‘Support vector regression based indoor location in IEEE 802.11 environments’, Mob. Inf. Syst., 2015, 201, no. Article ID 295652, p. 14.
-
-
36)
-
18. Kasparick, M., Cavalcante, R.L.G., Valentin, S., et al: ‘Kernel-based adaptive online reconstruction of coverage maps with side information’, IEEE Trans. Veh. Technol., 2016, 65, (7), pp. 5461–5473.
-
-
37)
-
36. Claesen, M., De Moor, B.: ‘Hyperparameter search in machine learning’. 11th Metaheuristics Int. Conf., 2015, pp. 10–14.
-
-
38)
-
3. Cernanský, M., Tino, P.: ‘Predictive modeling with echo state networks’. Artificial Neural Networks-ICANN 2008, 2008, no. 2.
-
-
39)
-
30. Verstraeten, D., Schrauwen, B., Dieleman, S., et al: ‘Oger: modular learning architectures for large-scale sequential processing’, J. Mach. Learn. Res., 2012, 13, pp. 2995–2998.
-
-
40)
-
39. James, G., Witten, D., Hastie, T., et al: ‘An introduction to statistical learning’ (Springer, 2013), vol. 64, no. 9–12.
-
-
41)
-
13. Baştanlar, Y., Ozuysal, M.: ‘Introduction to machine learning’, Methods Mol. Biol., 2014, 1107, pp. 105–128.
-
-
42)
-
7. Slavakis, K., Yamada, I., Ogura, N.: ‘The adaptive projected subgradient method over the fixed point set of strongly attracting nonexpansive mappings’, Numer. Funct. Anal. Optim., 2006, 27, (7–8), pp. 905–930.
-
-
43)
-
42. Ramirez, D.E.: ‘The generalized F distribution’, J. Stat. Softw., 2000, 5, (1), pp. 1–14.
-
-
44)
-
32. Lee, Y.-J., Hsieh, W.-F., Huang, C.-M.: ‘epsilon-SSVR: a smooth support vector machine for epsilon-insensitive regression’, IEEE Trans. Knowl. Data Eng., 2005, 17, (5), pp. 678–685.
-
-
1)