Advertisement

Artificial Intelligence Review

, Volume 52, Issue 1, pp 169–195 | Cite as

Primary user characterization for cognitive radio wireless networks using a neural system based on Deep Learning

  • Danilo LópezEmail author
  • Edwin Rivas
  • Oscar Gualdron
Article
  • 838 Downloads

Abstract

Cognitive radio is a paradigm that proposes maximizing the utilization of the usable radio-electric spectrum, allowing licensed users (PUs) and non-licensed users (SUs) to simultaneously coexist through the dynamic management and assignment of spectrum resources, by integrating the stages of spectrum sensing, decision, sharing and mobility. Spectrum decision is one of the most important stages, but its optimal operation depends on the characterization sub-stage, which is in charge of efficiently estimating time gaps in which a PU won’t make use of the assigned spectrum, so that it can be used in an opportunistic fashion by SUs. The design and implementation of an algorithm based on the Long Short-Term Memory (LSTM) recurrent neural network is proposed in order to increase the success percentage in the forecasting (presence/absence) of PUs in spectrum channels. The accuracy level exhibited in the results indicates LSTM increases the prediction percentage as compared to the Multilayer Perceptron Neural Network (MLPNN) and the Adaptative Neuro-Fuzzy Inference System (ANFIS) learning models, which means it could be implemented in cognitive networks with centralized physical topologies.

Keywords

Cognitive radio Long-Short Term Memory Neural network Deep Learning GSM 

References

  1. Adeel A, Larijani H, Ahmadinia. A (2014) Performance analysis of artificial neural network-based learning schemes for cognitive radio systems in LTE-UL. In: 28th International conference on advanced information networking and applications workshops (WAINA), May 13–16, Victoria, Canada, May 13–16Google Scholar
  2. Akyildiz I, Lee W-Y, Chowdhury K (2009) CRAHNS: cognitive radio ad hoc networks. Elsevier, Ad Hoc Networks , vol 7, pp. 810–836.  https://doi.org/10.1109/mnet.2009.5191140
  3. Akyildiz I, Lee W-Y Chowdhury, K (2014) Spectrum management in cognitive radio Ad Hoc networks. IEEE Network 2009, vol 23, pp. 6–12. Available online: http://ieeexplore.ieee.org (Accessed on 15 Oct 2014)
  4. Artiemjew P, Jiao N (2015) Data mining and machine learning. In: Yao Y, Hu Q, Yu H, Grzymala-Busse J (eds) Rough sets fussy sets in data mining and granular computing. Springer, Tianjin, pp 267–280CrossRefGoogle Scholar
  5. Banaei A, Georghiades C (2009) Throughput analysis of a randomized sensing scheme in cell-based Ad-hoc cognitive networks. In: IEEE international conference on communications, Dresden, Germany, June 14–18Google Scholar
  6. Bkassiny M, Li Y, Jayaweera S (2011) A survey on machine-learning techniques in cognitive radio department of electrical and computer engineering. University of New Mexico, MexicoGoogle Scholar
  7. Canberk B, Akyildiz I, Oktug S (2011) Primary user activity modeling using first-difference filter clustering and correlation in cognitive radio networks. IEEE/ACM Trans Netw 19:170–183.  https://doi.org/10.1109/TNET.2010.2065031
  8. Federal Communications Commission (2003) Notice of proposed rulemaking and order, Mexico D.F: Report ET Docket No: 03–332Google Scholar
  9. Fortuna C, Mohorcic M (2009) Trends in the development of communication networks: cognitive networks. J Comput Netw 53:1354–1376CrossRefGoogle Scholar
  10. Gers F, Schmidhuber E (2001) LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE Trans Neural Netw 12:1333–1340.  https://doi.org/10.1109/72.963769 CrossRefGoogle Scholar
  11. Ghosh C, Pagadarai S, Agrawal D, Wyglinski A (2010) A framework for statistical wireless spectrum occupancy modelling. IEEE Trans Wireless Commun 1:38–44.  https://doi.org/10.1109/TWC.2010.01.081701 CrossRefGoogle Scholar
  12. Graves A (2012) Supervised sequence labelling with recurrent neural networks. Springer, Heidelberg, pp. 37–93. ISBN 978-3-642-24796-5Google Scholar
  13. Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural network. In: IEEE international conference on acoustics speech and signal processing, Vancouver, Canada, May 23–26Google Scholar
  14. Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. In: IEEE international joint conference on neural network, Montreal, Canada, June 31–August 4Google Scholar
  15. Gutiérrez L, Zazo S, Murillo J, Álvarez I, Garcia A, Pérez B (2013) HF spectrum activity prediction model based on HMM for cognitive radio applications. Elsevier, Phys Commun, vol 9, pp. 199–211.  https://doi.org/10.1016/j.phycom.2012.09.004
  16. He A, Bae K, Newman T, Gaeddert J, Kim K, Menon R, Tirado L, Neel J, Zhao Y, Reed J, Tranter W (2010) A survey of artificial intelligence for cognitive radios. IEEE Trans Veh Technol 59:1578–1592.  https://doi.org/10.1109/tvt.2010.2043968 CrossRefGoogle Scholar
  17. Hernández C, Salgado L, López H, Rodríguez-Colina E (2015) Multivariable algorithm for dynamic channel selection in cognitive radio networks. EURASIP J Wireless Commun Netw, vol 2015, Issue 1, pp. 1–17. Available online: http://jwcn.eurasipjournals.springeropen.com/articles/10.1186/s13638-015-0445-8  https://doi.org/10.1186/s13638-015-0445-8
  18. Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. J Neural Comput 9:1735–1780.  https://doi.org/10.1162/neco.1997.9.8.1735 CrossRefGoogle Scholar
  19. IEEE Standard 1900.1 (2008) IEEE standard definitions and concepts for dynamic spectrum access: terminology relating to emerging wireless network, system functionality and spectrum managementGoogle Scholar
  20. Kalkan S (2015) Special topics in Deep Learning. Middle East Technical University, Ankara, Turquia, Available online: http://www.kovan.ceng.metu.edu.tr/~sinan/DL/
  21. Khabazian M, Aissa S, Tadayon N (2012) Performance modeling of a two-tier primary-secondary network operated with IEEE802.11 DCF mechanism. IEEE Trans Wireless Commun, pp. 3047–3057Google Scholar
  22. Khalid L, Anpalagan A (2014) Emerging cognitive radio technology: principles, challenges and opportunities. Elsevier, Computers and Electrical Engineering 2010, vol 38, pp. 358–366. Available online: http://www.sciencedirect.com/science/article/pii/S0045790609000524.  https://doi.org/10.1016/j.compeleceng.2009.03.004. (Accessed on 20 Oct 2014)
  23. Kwok T-Y, Yeung D-Y (1997) Constructive algorithms for structure learning in feedforward neural networks for regresission problems. In: IEEE transactions on neural networks, vol 8, pp. 630–645. Available online: http://ieeexplore.ieee.org/Xplore/home.jsp.  https://doi.org/10.1109/72.572102. (Accessed on 21 June 2013)
  24. Lee W-Y, Akyildiz I (2011) A spectrum decision framework for cognitive radio networks. IEEE Trans Mobile Comput 10:161–174.  https://doi.org/10.1109/TMC.2010.147 CrossRefGoogle Scholar
  25. López D, Ordoñez J, Trujillo E (2016) User characterization through dynamic bayesian networks in cognitive radio wireless networks. Int J Eng Technol 8:1771–1783CrossRefGoogle Scholar
  26. López D, Hernández L, Rivas E (2017) SVM and ANFIS as channel selection models for the spectrum decision stage in cognitive radio networks. Contemp Eng Sci 10:475–502CrossRefGoogle Scholar
  27. López D, Trujillo E, Gualdron O (2015) Elementos fundamentales que componen la radio cognitiva y asignación de bandas espectrales. Información tecnológica. vol 26, pp. 23–40. Available online: http://www.scielo.cl/pdf/infotec/v26n1/art04.pdf.  https://doi.org/10.4067/s0718-07642015000100004. (Accessed on 10 Mar 2015)
  28. Masonta M, Mzyece M, Ntlatlapa N (2013) Spectrum decision in cognitive radio networks: a survey. IEEE Commun Soc Commun Surv Tutor, vol 15, pp. 1088–1107. Available online: http://ieeexplore.ieee.org.  https://doi.org/10.1109/surv.2012.111412.00160. (Accessed on 15 Aug 2014)
  29. Masters T (1993) Multilayer feedforward networks. In practical neural network recipes in C++. Academic Press, San Diego, pp 77–116Google Scholar
  30. Palangi H, Deng L, Shen Y, Gao J, He X, Chen J, Song X, Ward R (2016) Deep sentence embedding using Long Short-Term Memory Networks: analysis and application to information retrieval. IEEE/ACM Trans Audio Speech Lang Process 24:694–707.  https://doi.org/10.1109/TASLP.2016.2520371 CrossRefGoogle Scholar
  31. Palangi H, Ward R, Deng L (2015) Distributed compressive sensing: a deep learning approach, Cornell University Library, arXiv. Available online: https://arxiv.org/abs/1508.04924 (Accessed on 17 Sept 2015)
  32. Pattanayak S, Venkateswaran P, Nandi R (2013) Artificial intelligence based model for channel status prediction?: A new spectrum sensing technique for cognitive radio. Int J Commun Netw Syst Sci (IJCNS), Kolkata, April 4–7Google Scholar
  33. Pedraza L, Hernández C, Galeano K, Rodriguez-Colina E (2016) Ocupación espectral y modelo de radio cognitiva para Bogotá. Universidad Distrital Francisco José de Caldas Publisher: UD EditorialGoogle Scholar
  34. Popescu OA, Yao Y, Fiedler M, Popescu PA (2014) A management architecture for multimedia communication in cognitive radio networks. In: Fei Hu, Kumar Sunil (eds) Multimedia over cognitive radio networks. CRC Press, London, pp 3–25Google Scholar
  35. Sahai A, Hoven N, Tandra R (2015) Some fundamental limits on cognitive radio. Department electrical engineering and computer science. University of California. Available online: http://www.eecs.berkeley.edu/~sahai/Papers/cognitive_radio_preliminary.pdf (Accessed on 17 Jan 2015)
  36. Saleem Y, Rehmani M (2014) Primary radio user activity models for cognitive radio networks: a survey. J Netw Comput Appl, vol 43, pp. 1–16. Available online: http://www.sciencedirect.com/science/article/pii/S1084804514000848  https://doi.org/10.1016/j.jnca.2014.04.001
  37. Salgado L (2014) Algoritmo multivariable para la selección dinámica del canal de backup en redes de radio cognitiva basado en el método Fuzzy Analitical Hierarchical Process. Faculty of Engineering University Distrital Francisco Jose de Caldas, BogotáGoogle Scholar
  38. Shared Spectrum Company (2015) Spectrum reports: spectrum occupancy measurement. General survey of radio frequency bands (30 MHz to 3 GHz): Vienna, Virginia. Available online: http://www.sharedspectrum.com/papers/spectrum-reports/ (Accessed on 7 June 2015)
  39. Sun B, Feng H, Chen K, Zhu X (2016) A deep learning framework of quantized compressed sensing for wireless neural recording. J IEEE Access 4:5169–5178CrossRefGoogle Scholar
  40. Sundermeyer M, Ney H, Schlüter R (2016) From feedforward to recurrent LSTM neural networks for language modeling. IEEE/ACM Trans Audio Speech Lang Process 23:517–529.  https://doi.org/10.1109/TASLP.2015.2400218 CrossRefGoogle Scholar
  41. Tumuluru V, Wang P, Niyato D (2010) A neural network based spectrum prediction scheme for cognitive radio. IEEE International Conference on Communications (ICC), Cape Town, May pp. 23–27Google Scholar
  42. Uyanik G, Canberk B, Oktug S (2012) Predictive spectrum decision mechanisms in Cognitive Radio Networks. In: IEEE Globecom Workshop, Anaheim, December 3–7Google Scholar
  43. Veeriah V Zhuang N, Qi G-J (2015) Differential recurrent neural networks for action recognition. In: IEEE international conference on computer vision (ICCV), Santiago, Chile, December 7–13Google Scholar
  44. Wang J, Ghosh M, Challapali K (2011) Emerging cognitive radio applications: a survey. IEEE Commun Mag 49:74–81.  https://doi.org/10.1109/mcom.2011.5723803 CrossRefGoogle Scholar
  45. Winston O, Thomas A, OkelloOdongo W (2014) Optimizing neural network for TV Idle channel prediction in cognitive radio using particle swarm optimization. In: Fifth international conference on computational intelligence, communication systems and networks (CICSyN), Madrid, Spain, June 5–7Google Scholar
  46. Yarkan S, Arslan H (2013) Binary time series approach to spectrum prediction for cognitive radio. In: IEEE vehicular technology conference, Baltimore, September/October, 30–3Google Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2017

Authors and Affiliations

  1. 1.Faculty of EngineeringDistrital UniversityBogotáColombia
  2. 2.Faculty of EngineeringPamplona UniversityPamplonaColombia

Personalised recommendations