Spectrum Prediction for Cognitive Radio System Based on Optimally Pruned Extreme Learning Machine

Abstract:

The Cognitive Radio (CR) technology is an efficient solution to spectrum scarcity by share the spectrum with the secondary users on a non-interfering basis. The spectrum prediction can rationalize the spectrum allocation based on previous information about the spectrum evolution in time. Against previous spectrum prediction algorithm lack of timeliness and accuracy, this paper proposes a novel approach for spectrum prediction based on Optimally Pruned Extreme Learning Machine (OP-ELM) which improved the original Extreme Learning Machine (ELM) algorithm. This method not only takes the advantage of the ELM extremely fast speed and good precision, but also more robust and generic with additional steps compared with ELM. In order to compare its comprehensive properties to other algorithms, some experiments were designed. The results show that the predictive performance of this new algorithm is more satisfaction than others in spectrum prediction problem.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 430-436
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.430
• Online since: April 2014
• Authors: Ling Yang, Na Lv*, Zhen Xing Xu
• Keywords: Cognitive Radio (CR), Extreme Learning Machine, Spectrum Prediction, Spectrum Sensing, Time Series

References

[1] S. Haykin, Cognitive radio: Brain-empowered wireless communications, IEEE Journal on Selected Areas in Communications, Vol. 23, No. 2, 2005, pp.201-220.

DOI: 10.1109/jsac.2004.839380

[2] T. V. Krishna and A. Das, A survey on MAC protocols in OSA networks, Computer Networks, 53, 2009, pp.1377-1394.

DOI: 10.1016/j.comnet.2009.01.003

[3] N. Shah, T. Kamakaris, U. Tureli, and M. Buddhikot, Wideband spectrum sensing probe for distributed measurements in cellular band, Proceedings of the first international workshop on Technology and policy for accessing spectrum, No. 13, 2006, pp.1-6.

DOI: 10.1145/1234388.1234401

[4] S. Yarkan, and H. Arslan, Binary time series approach to spectrum prediction for cognitive radios, IEEE 66th Vehicular Technology Conference, 2007, pp.1563-1567.

DOI: 10.1109/vetecf.2007.332

[5] I.A. Akbar, and W. H Tranter, Dynamic spectrum allocation in cognitive radio using hidden Markov models: Poisson distributed case, SoutheastCon Proceedings. IEEE, 2007, pp.196-201.

DOI: 10.1109/secon.2007.342884

[6] Li Y, Dong Y, Zhang H, et al, Spectrum usage prediction based on high-order Markov model for cognitive radio networks, IEEE 10th International Conference on CIT, 2010, pp.2784-2788.

DOI: 10.1109/cit.2010.464

[7] V.K. Tumuluru, D. Niyato, and Ping Wang, A neural network based spectrum prediction scheme for cognitive radio, IEEE International Conference on ICC, 2010, pp.1-5.

DOI: 10.1109/icc.2010.5502348

[8] Yin Liang, et al, Spectrum behavior learning in Cognitive Radio based on artificial neural network,  MILITARY COMMUNICATIONS CONFERENCE, 2011, pp.25-30.

DOI: 10.1109/milcom.2011.6127671

[9] M. I. Taj,  and M. Akil, Cognitive Radio spectrum evolution prediction using artificial neural networks based multivariate time series modeling, Wireless Conference 2011 - Sustainable Wireless Technologies (European Wireless) 11th European, 2011, pp.670-675.

[10] A. Katidiotis, K. Tsagkaris, and P. Demestichas, Performance evaluation of artificial neural network-based learning schemes for cognitive radio systems,  Computers & Electrical Engineering, Vol. 36, No. 3, 2010, pp.518-535.

DOI: 10.1016/j.compeleceng.2009.12.005

[11] C.B. Xu, et al, A Novel Spectrum Prediction Algorithm for Cognitive Radio System Based on Chaotic Neural Network, Journal of Computational Information Systems, Vol. 9, no. 1, 2013, pp.313-320.

[12] Yang Ling, et al, Spectrum Prediction Based on Echo State Network and Its Improved Form, Intelligent Human-Machine Systems and Cybernetics (IHMSC), vol. 1, 2013, pp.172-176.

DOI: 10.1109/ihmsc.2013.48

[13] M.Z. Hong, et al, A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks, Neural Networks, Vol. 17, No. 6, 2006, pp.1580-1591.

DOI: 10.1109/tnn.2006.880360

[14] G.B. Huang, Q.Y. Zhu, C.K. Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, Neural Networks, vol. 2, 2004, p.985–990.

DOI: 10.1109/ijcnn.2004.1380068

[15] G.B. Huang, Q.Y. Zhu, C.K. Siew, Extreme learning machine: theory and applications, Neurocomputing , Vol. 70, No. 1-3, 2006, pp.489-501.

DOI: 10.1016/j.neucom.2005.12.126

[16] G.B. Huang, D.H. Wang, Y Lan, Extreme learning machines: a survey, International Journal of Machine Learning and Cybernetics, 2011, pp.107-122.

[17] Y. Miche, et al, OP-ELM: optimally pruned extreme learning machine, Neural Networks, IEEE Transactions on, Vol. 21,  No. 1, 2010, pp.158-162.

DOI: 10.1109/tnn.2009.2036259

[18] G.B. Huang, C. Lei, Convex incremental extreme learning machine, Neurocomputing , Vol. 70, No. 16–18, 2007, pp.3056-3062.

DOI: 10.1016/j.neucom.2007.02.009

[19] G.B. Huang, C. Lei, C.K. Siew, Universal approximation using incremental constructive feedforward networks with random hidden nodes, Neural Networks, IEEE Transactions on , Vol. 17,  No. 4, 2006, pp.879-892.

DOI: 10.1109/tnn.2006.875977

[20] G.B. Huang, C.K. Siew, Extreme learning machine: RBF network case, Control, Automation, Robotics and Vision Conference, Vol. 2 , 2004, pp.1029-1036.

DOI: 10.1109/icarcv.2004.1468985

[21] G.B. Huang, et al, Can threshold networks be trained directly?, Circuits and Systems II: Express Briefs, Vol. 53,  No. 3, 2006, pp.187-191.

DOI: 10.1109/tcsii.2005.857540

[22] C.R. Rao, S.K. Mitra, Generalized Inverse of Matrices and Its Applications, Wiley  (New York), (1972).

[23] T. Similä, J. Tikka, Multiresponse sparse regression with application to multidimensional scaling, Artificial Neural Networks: Formal Models and Their Applications, vol. 36, 2005, pp.97-102.

DOI: 10.1007/11550907_16

[24] R.H. Myers, Classical and Modern Regressionwith Applications, Pacific Grove, (1990).

[25] G. Bontempi, M. Birattari, H. Bersini, Recursive lazy learning for modeling and control, Lecture Notes in Computer Science, Vol. 1398, 1998, pp.292-303.

DOI: 10.1007/bfb0026699

[26] Hoyhtya, Marko, P. Sofie, M. Aarne, Performance improvement with predictive channel selection for cognitive radios, Cognitive Radio and Advanced Spectrum Management, 2008, pp.1-5.

DOI: 10.1109/cogart.2008.4509983