Wireless channel feature extraction via GMM and CNN in the tomographic channel model

Research Paper
  • 163 Downloads

Abstract

Wireless channel modeling has always been one of the most fundamental highlights of the wireless communication research. The performance of new advanced models and technologies heavily depends on the accuracy of the wireless CSI (Channel State Information). This study examined the randomness of the wireless channel parameters based on the characteristics of the radio propagation environment. The diversity of the statistical properties of wireless channel parameters inspired us to introduce the concept of the tomographic channel model. With this model, the static part of the CSI can be extracted from the huge amount of existing CSI data of previous measurements, which can be defined as the wireless channel feature. In the proposed scheme for obtaining CSI with the tomographic channel model, the GMM (Gaussian Mixture Model) is applied to acquire the distribution of the wireless channel parameters, and the CNN (Convolutional Neural Network) is applied to automatically distinguish different wireless channels. The wireless channel feature information can be stored offline to guide the design of pilot symbols and save pilot resources. The numerical results based on actual measurements demonstrated the clear diversity of the statistical properties of wireless channel parameters and that the proposed scheme can extract the wireless channel feature automatically with fewer pilot resources. Thus, computing and storage resources can be exchanged for the finite and precious spectrum resource.

Keywords

wireless channel modeling tomographic channel model Gaussian mixture model convolutional neural network 

References

  1. [1]
    G. E. Athanasiadou, A. R. Nix. A novel 3-D indoor raytracing propagation model: the path generator and evaluation of narrow-band and wide-band predictions [J]. IEEE transactions on vehicular technology, 2000, 49(4): 1152–1168.CrossRefGoogle Scholar
  2. [2]
    J. Poutanen. Geometry-based radio channel modeling: propagation analysis and concept development [D]. Helsinki: Aalto University, 2011.Google Scholar
  3. [3]
    R. Verdone, A. Zanella. Pervasive mobile and ambient wireless communications: COST action 2100 [M]. Springer Science & Business Media, 2012.CrossRefGoogle Scholar
  4. [4]
    J. Meinilä, P. Kyösti, T. Jämsä, et al. WINNER II channel models [C]//Radio Technologies and Concepts for IMT-Advanced, Wiley, 2009: 39–92.CrossRefGoogle Scholar
  5. [5]
    J. Meinila, P. Kyosti, L. Hentila, et al. D5.3: WINNER+ final channel models. Wireless World Initiative New Radio WINNER, 2010.Google Scholar
  6. [6]
    S. Jaeckel, L. Raschkowski, K. Börner, et al. QuaDRiGa-Quasi deterministic radio channel generator, user manual and documentation [R]. Fraunhofer Heinrich Hertz Institute, 2014.Google Scholar
  7. [7]
    A. Maltsev, V. Erceg, E. Perahia, et al. Channel models for 60 GHz WLAN systems [EB/OL]. IEEE doc, 2010: 802.11-09.Google Scholar
  8. [8]
    J. Karedal, F. Tufvesson, N. Czink, et al. A geometrybased stochastic MIMO model for vehicle-to-vehicle communications [J]. IEEE transactions on wireless communications, 2009, 8(7): 3646–3657.CrossRefGoogle Scholar
  9. [9]
    J. Medbo, K. Börner, K. Haneda, et al. Channel modelling for the fifth generation mobile communications [C]//The 8th European Conference on Antennas and Propagation (EuCAP), The Hague, Netherlands, 2014: 219–223.Google Scholar
  10. [10]
    C. X. Wang, A. Ghazal, B. Ai, et al. Channel measurements and models for high-speed train communication systems: a survey [J]. IEEE communications surveys & tutorials, 2016, 18(2): 974–987.CrossRefGoogle Scholar
  11. [11]
    J. Z. Wang, H. L. Zhu, N. J. Gomes. Distributed antenna systems for mobile communications in high speed trains [J]. IEEE journal on selected areas in communications, 2012, 30(4): 675–683.CrossRefGoogle Scholar
  12. [12]
    B. H. Chen, Z. D. Zhong, B. Ai, et al. Channel characteristics in high-speed railway: a survey of channel propagation properties [J]. IEEE vehicular technology magazine, 2015, 10(2): 67–78.CrossRefGoogle Scholar
  13. [13]
    M. Metis. Wireless communications enablers for the Twentytwenty Information Society. EU 7th Framework Programme project [R]. ICT-317669-METIS.Google Scholar
  14. [14]
    M. Fallgren, B. Timus. Future radio access scenarios, requirements and KPIs [J]. METIS deliverable D, 2013, 1.Google Scholar
  15. [15]
    A. Osseiran, F. Boccardi, V. Braun, et al. Scenarios for 5G mobile and wireless communications: the vision of the METIS project [J]. IEEE communications magazine, 2014, 52(5): 26–35.CrossRefGoogle Scholar
  16. [16]
    X. H. Wang, E. Anderson, P. Steenkiste, et al. Improving the accuracy of environment-specific channel modeling [J]. IEEE transactions on mobile computing, 2016, 15(4): 868–882.CrossRefGoogle Scholar
  17. [17]
    X. H. Wang, E. Anderson, P. Steenkiste, et al. Improving the accuracy of environment-specific vehicular channel modeling [C]//The 7th ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation and Characterization, Istanbul, Turkey, 2012: 43–50.Google Scholar
  18. [18]
    M. Boban, J. Barros, O. K. Tonguz. Geometry-based vehicle-to-vehicle channel modeling for large-scale simulation [J]. IEEE transactions on vehicular technology, 2014, 63(9): 4146–4164.CrossRefGoogle Scholar
  19. [19]
    J. Medbo, H. Asplund, J. E. Berg, et al. Directional channel characteristics in elevation and azimuth at an urban macrocell base station [C]//The 6th European Conference on Antennas and Propagation (EUCAP), Prague, Czech Republic, 2012: 428–432.Google Scholar
  20. [20]
    H. H. Li, Y. Z. Li, S. D. Zhou, et al. A novel method to obtain CSI based on Gaussian mixture model and expectation maximization [C]//The 8th International Conference on Wireless Communications & Signal Processing (WCSP), Yangzhou, China, 2016: 1–5.Google Scholar
  21. [21]
    D. Tse, P. Viswanath. Fundamentals of wireless communication [M]. Cambridge: Cambridge University Press, 2005.CrossRefMATHGoogle Scholar
  22. [22]
    Y. Zhang, S. J. Liu, Y. H. Rui, et al. Wideband wireless channel predictor relying on environment information [C]//The 8th International Symposium on Antennas, Propagation and EM Theory (ISAPE), Kunming, China, 2008: 945–948.Google Scholar
  23. [23]
    Y. Zhang, S. J. Liu, Y. H. Rui, et al. Channel prediction assisted by radio propagation environments information [C]//The 4th IEEE International Conference on Circuits and Systems for Communications (ICCSC), Shanghai, China, 2008: 733–736.Google Scholar
  24. [24]
    L. Tong, B. M. Sadler, M. Dong. Pilot-assisted wireless transmissions: general model, design criteria, and signal processing [J]. IEEE signal processing magazine, 2004, 21(6): 12–25.CrossRefGoogle Scholar
  25. [25]
    B. H. Fleury, P. Jourdan, A. Stucki. High-resolution channel parameter estimation for MIMO applications using the SAGE algorithm [C]//International Zurich Seminar on Broadband Communications AccessTransmission-Networking, Zurich, Switzerland, 2002: 30–30.Google Scholar
  26. [26]
    Z. Zivkovic. Improved adaptive Gaussian mixture model for background subtraction [C]//The 17th International Conference on Pattern Recognition (ICPR), Cambridge, UK, 2004, 2: 28–31.Google Scholar
  27. [27]
    T. Toda, A. W. Black, K. Tokuda. Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model [J]. Speech communication, 2008, 50(3): 215–227.CrossRefGoogle Scholar
  28. [28]
    T. K. Moon. The expectation-maximization algorithm [J]. IEEE signal processing magazine, 1996, 13(6): 47–60.CrossRefGoogle Scholar
  29. [29]
    Y. Bengio. Learning deep architectures for AI [J]. Foundations and trends in Machine Learning, 2009, 2(1): 1–127.MathSciNetCrossRefMATHGoogle Scholar
  30. [30]
    J. Bouvrie. Notes on convolutional neural networks [EB/OL]. http://cogprints.org/5869/1/cnn tutorial. pdf, 2006.Google Scholar
  31. [31]
    Y. LeCun, Y. Bengio. Convolutional networks for images, speech, and time series [C]//The handbook of brain theory and neural networks, MIT Press, Cambridge, USA, 1998: 255–258.Google Scholar

Copyright information

© Posts & Telecom Press and Springer Singapore 2017

Authors and Affiliations

  • Haihan Li
    • 1
    • 2
  • Yunzhou Li
    • 2
  • Shidong Zhou
    • 1
    • 2
  • Jing Wang
    • 2
  1. 1.Department of Electronic EngineeringTsinghua UniversityBeijingChina
  2. 2.Tsinghua National Laboratory for Information Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations