Skip to main content
SpringerLink
Log in

Proposal of Online Regularization for Dynamical Structure Optimization in Complex-Valued Neural Networks

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2019)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 11954))

Included in the following conference series:

Abstract

We propose online-learning complex-valued neural networks (CVNN) to predict future channel states in fast fading multipath mobile communications. A communication channel is represented by complex amplitude. Then, CVNNs are intrinsically suitable for fading channel prediction by utilizing its high generalization ability in the complex-amplitude domain. In this paper, we introduce regularization dynamics to make the CVNN structure dynamically changing in accordance with the changes in the multipath situations. We demonstrate the online adaptability when the scattering environment changes.

A. Hirose—A part of this work was supported by JSPS KAKANHI under Grant 15H02756 and Grant 18H04105, and a part by Tohoku University RIEC Cooperative Research Project.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Arima, Y., Hirose, A.: Performance dependence on system parameters in millimeter-wave active imaging based on complex-valued neural networks to classify complex texture. IEEE Access 5, 22927–22939 (2017). http://ieeexplore.ieee.org/document/8036195/

    Article  Google Scholar 

  2. Arredondo, A., Dandekar, K., Xu, G.: Vector channel modeling and prediction for the improvement of downlink received power. IEEE Trans. Commun. 50(7), 1121–1129 (2002). http://ieeexplore.ieee.org/document/1021044/

    Article  Google Scholar 

  3. Barakat, M., Druaux, F., Lefebvre, D., Khalil, M., Mustapha, O.: Self adaptive growing neural network classifier for faults detection and diagnosis. Neurocomputing 74(18), 3865–3876 (2011). https://doi.org/10.1016/j.neucom.2011.08.001. http://linkinghub.elsevier.com/retrieve/pii/S0925231211004425

    Article  Google Scholar 

  4. Bui, H.P., Ogawa, Y., Nishimura, T., Ohgane, T.: Performance evaluation of a multi-user MIMO system with prediction of time-varying indoor channels. IEEE Trans. Antennas Propag. 61(1), 371–379 (2013). http://ieeexplore.ieee.org/document/6280628/

    Article  Google Scholar 

  5. Bui, N., Cesana, M., Hosseini, S.A., Liao, Q., Malanchini, I., Widmer, J.: A survey of anticipatory mobile networking: context-based classification, prediction methodologies, and optimization techniques. IEEE Commun. Surv. Tutorials 19(3), 1790–1821 (2017). http://ieeexplore.ieee.org/document/7904647/

    Article  Google Scholar 

  6. Candès, E.J., Romberg, J.K., Tao, T.: Stable signal recovery from incomplete and inaccurate measurements. Commun. Pure Appl. Math. 59(8), 1207–1223 (2006). https://doi.org/10.1002/cpa.20124

    Article  MathSciNet  MATH  Google Scholar 

  7. Cho, Y.S., Kim, J., Yang, W.Y., Kang, C.G.: MIMO-OFDM Wireless Communications with MATLAB®. Wiley, Chichester (2010). https://doi.org/10.1002/9780470825631

    Book  Google Scholar 

  8. Ding, T., Hirose, A.: Fading channel prediction based on combination of complex-valued neural networks and chirp Z-transform. IEEE Trans. Neural Netw. Learn. Syst. 25(9), 1686–1695 (2014). https://doi.org/10.1007/978-3-319-12637-1_22. http://ieeexplore.ieee.org/document/6755477/

    Article  Google Scholar 

  9. Ding, T., Hirose, A.: Fading channel prediction based on self-optimizing neural networks. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds.) ICONIP 2014. LNCS, vol. 8834, pp. 175–182. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-12637-1_22

    Chapter  Google Scholar 

  10. Donoho, D.L., Tanner, J.: Counting faces of randomly projected polytopes when the projection radically lowers dimension. J. Am. Math. Soc. 22(1), 1–53 (2008). http://www.ams.org/journal-getitem?pii=S0894-0347-08-00600-0

    Article  MathSciNet  Google Scholar 

  11. Duel-Hallen, A.: Fading channel prediction for mobile radio adaptive transmission systems. Proc. IEEE 95(12), 2299–2313 (2007). http://ieeexplore.ieee.org/document/4389753/

    Article  Google Scholar 

  12. Duel-Hallen, A., Hallen, H., Yang, T.-S.: Long range prediction and reduced feedback for mobile radio adaptive OFDM systems. IEEE Trans. Wirel. Commun. 5(10), 2723–2733 (2006). http://ieeexplore.ieee.org/document/1705934/

    Article  Google Scholar 

  13. Elad, M.: Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing. Springer, Berlin (2010)

    Book  Google Scholar 

  14. Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48(1), 71–99 (1993). http://linkinghub.elsevier.com/retrieve/pii/0010027793900584

    Article  Google Scholar 

  15. Eraslan, E., Daneshrad, B., Lou, C.Y.: Performance indicator for MIMO MMSE receivers in the presence of channel estimation error. IEEE Wirel. Commun. Lett. 2(2), 211–214 (2013). http://ieeexplore.ieee.org/document/6425374/

    Article  Google Scholar 

  16. Eyceoz, T., Duel-Hallen, A., Hallen, H.: Deterministic channel modeling and long range prediction of fast fading mobile radio channels. IEEE Commun. Lett. 2(9), 254–256 (1998). http://ieeexplore.ieee.org/document/718494/

    Article  Google Scholar 

  17. Hara, T., Hirose, A.: Plastic mine detecting system using complex-valued self-organizing map that deals with multiple-frequency interferometric images. Neural Netw. 17(8–9), 1201–1210 (2004)

    Article  Google Scholar 

  18. Hirose, A.: Applications of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme. Inf. Sci.-Appl. 2, 103–117 (1994)

    Google Scholar 

  19. Hirose, A.: Complex-Valued Neural Networks, vol. 400, 2nd edn. Springer, New York (2012)

    Book  Google Scholar 

  20. Hirose, A., Eckmiller, R.: Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain. Appl. Optics 35(5), 836 (1996). https://doi.org/10.1002/rnc.592. https://www.osapublishing.org/abstract.cfm?URI=ao-35-5-836

    Article  Google Scholar 

  21. Hirose, A., Yoshida, S.: Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence. IEEE Trans. Neural Netw. Learn. Syst. 23, 541–551 (2012)

    Article  Google Scholar 

  22. Ishikawa, M.: Structural learning with forgetting. Neural Netw. 9(3), 509–521 (1996). http://linkinghub.elsevier.com/retrieve/pii/0893608096836963

    Article  Google Scholar 

  23. Jakes, W.: Microwave Mobile Communications, 2nd edn. Wiley, New York (1994). http://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=5263365%5Cnieeexplore.ieee.org/search/srchabstract.jsp?arnumber=5263390

    Book  Google Scholar 

  24. Karnin, E.: A simple procedure for pruning back-propagation trained neural networks. IEEE Trans. Neural Netw. 1(2), 239–242 (1990). http://ieeexplore.ieee.org/document/80236/

    Article  Google Scholar 

  25. Kawata, S., Hirose, A.: Frequency-multiplexed logic circuit based on a coherent optical neural network. Appl. Opt. 44(19), 4053–4059 (2005)

    Article  Google Scholar 

  26. Liu, W., Yang, L.L., Lajos, H.: Recurrent neural network based narrowband channel prediction. In: 2006 IEEE 63rd Vehicular Technology Conference, vol. 5, pp. 2173–2177. IEEE (2006). http://ieeexplore.ieee.org/document/1683241/

  27. Maehara, F., Sasamori, F., Tkahata, F.: Linear predictive maximal ratio combining transmitter diversity for OFDM-TDMA/TDD systems. IEICE Trans. Commun. E86–B(1), 221–229 (2003)

    Google Scholar 

  28. Potter, C., Venayagamoorthy, G.K., Kosbar, K.: RNN based MIMO channel prediction. Signal Process. 90(2), 440–450 (2010). http://linkinghub.elsevier.com/retrieve/pii/S0165168409003120

    Article  Google Scholar 

  29. Ramachandram, D., Taylor, G.W.: Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process. Mag. 34(6), 96–108 (2017). http://ieeexplore.ieee.org/document/8103116/

    Article  Google Scholar 

  30. Reed, R.: Pruning algorithms-a survey. IEEE Trans. Neural Netw. 4(5), 740–747 (1993). http://ieeexplore.ieee.org/document/248452/

    Article  Google Scholar 

  31. Ren, X., Wu, J., Johansson, K.H., Shi, G., Shi, L.: Infinite horizon optimal transmission power control for remote state estimation over fading channels. IEEE Trans. Autom. Control 63(1), 85–100 (2018). http://ieeexplore.ieee.org/document/7935515/

    Article  MathSciNet  Google Scholar 

  32. Sharma, P., Chandra, K.: Prediction of state transitions in rayleigh fading channels. IEEE Trans. Veh. Technol. 56(2), 416–425 (2007). http://ieeexplore.ieee.org/document/4138045/

    Article  Google Scholar 

  33. Sui, Y., Yu, W., Luo, Q.: Jointly optimized extreme learning machine for short-term prediction of fading channel. IEEE Access 6, 49029–49039 (2018). https://ieeexplore.ieee.org/document/8457080/

    Article  Google Scholar 

  34. Tan, S., Hirose, A.: Low-calculation-cost fading channel prediction using chirp Z-transform. Electron. Lett. 45(8), 418 (2009). http://digital-library.theiet.org/content/journals/10.1049/el.2009.3472

    Article  Google Scholar 

  35. Lu, T.-C., Yu, G.-R., Juang, J.-C.: Quantum-based algorithm for optimizing artificial neural networks. IEEE Trans. Neural Netw. Learn. Syst. 24(8), 1266–1278 (2013). http://ieeexplore.ieee.org/document/6507335/

    Article  Google Scholar 

  36. Valle, M.E.: Complex-valued recurrent correlation neural networks. IEEE Trans. Neural Netw. Learn. Syst. 25(9), 1600–1612 (2014). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6866912

    Article  Google Scholar 

  37. Zhao, Y., Gao, H., Beaulieu, N.C., Chen, Z., Ji, H.: Echo state network for fast channel prediction in ricean fading scenarios. IEEE Commun. Lett. 21(3), 672–675 (2017). http://ieeexplore.ieee.org/document/7755792/

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo, 153-8656, Japan

    Tianben Ding & Akira Hirose

  2. Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, 63130, USA

    Tianben Ding

Authors
  1. Tianben Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Akira Hirose
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Akira Hirose .

Editor information

Editors and Affiliations

  1. Australian National University, Canberra, ACT, Australia

    Tom Gedeon

  2. Murdoch University, Murdoch, WA, Australia

    Kok Wai Wong

  3. Kyungpook National University, Daegu, Korea (Republic of)

    Minho Lee

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ding, T., Hirose, A. (2019). Proposal of Online Regularization for Dynamical Structure Optimization in Complex-Valued Neural Networks. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11954. Springer, Cham. https://doi.org/10.1007/978-3-030-36711-4_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-36711-4_34

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-36710-7

  • Online ISBN: 978-3-030-36711-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation