Channel Compressed Estimation Based on k-Nearest Neighbor Learning

  • Hua-Feng ZhangEmail author
  • Chen-Guang HeEmail author
  • Wen-Bin Zhang
  • Kuo Zhao
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 463)


MmWave communication is receiving tremendous interest by academia, industry, and government for 5G cellular systems. Due to the short wavelength, the millimeter wave experiences high path loss and penetration loss. Compensating for path loss will require beamforming, which is based on channel estimation. However, in the actual environment, the number of multi-path is unknown. In order to solve the problem in millimeter wave system, this paper estimates the number of multi-path by utilizing k-Nearest Neighbor learning. Then we use the OMP algorithm to estimate the channel. The simulations show that the k-Nearest Neighbor learning can get better performance of channel estimations in the mmWave MIMO communication.


Hybrid analog/digital beamforming Channel estimation Millimeter wave MIMO Compressed sensing k-Nearest Neighbor learning 



This work was supported by the National Science and Technology Major Specific Projects of China (Grant No. 2015ZX03004002-004).


  1. 1.
    Pi, Z., Khan, F.: An introduction to millimeter-wave mobile broadband systems. IEEE Commun. Mag. 49(6), 101–107 (2011)Google Scholar
  2. 2.
    Andrews, J.G., et al.: What will 5G be? IEEE J. Sel. Areas Commun. 32(6), 1065–1082 (2014)Google Scholar
  3. 3.
    Pyattaev, A., Johnsson, K., Andreev, S., Koucheryavy, Y.: Communication challenges in high-density deployments of wearable wireless devices. IEEE Wireless Commun. 22(1), 12–18 (2015)Google Scholar
  4. 4.
    El Ayach, O., Rajagopal, S., Abu-Surra, S., Pi, Z., Heath Jr., R.W.: Spatially sparse precoding in millimeter wave MIMO systems. IEEE Trans. Wireless Commun. 13(3), 1499–1513 (2014)Google Scholar
  5. 5.
    Venkateswaran, V., van der Veen, A.: Analog beamforming in MIMO communications with phase shift networks and online channel estimation. IEEE Trans. Signal Process. 58(8), 4131–4143 (2010)Google Scholar
  6. 6.
    Alkhateeb, A., El Ayach, O., Leus, G., Heath Jr., R.W.: Hybrid precoding for millimeter wave cellular systems with partial channel knowledge. In: Proceedings Information Theory and Applications Workshop (ITA), pp. 1–5, February 2013Google Scholar
  7. 7.
    Alkhateeb, A., El Ayach, O., Leus, G., Heath Jr., R.W.: Channel estimation and hybrid precoding for millimeter wave cellular systems. IEEE J. Sel. Topics Signal Process. 8(5), 831–846 (2014)Google Scholar
  8. 8.
    El Ayach, O., Heath Jr., R.W., Rajagopal, S., Pi, Z.: Multimode precoding in millimeter wave MIMO transmitters with multiple antenna sub-arrays. In: Proceedings IEEE Global Telecommunication Conference (GLOBECOM), pp. 3476–3480, December 2013Google Scholar
  9. 9.
    Heath Jr., R.W., Gonzalez-Prelcic, N., Rangan, S., Roh, W., Sayeed, A.: An overview of signal processing techniques for millimeter wave MIMO systems. IEEE J. Special Topics Signal Process (to be published).
  10. 10.
    Jiang, L.: Survey of improving K-nearest-neighbor for classification. In: Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007), pp. 679–683 (2007).
  11. 11.
    Jiang, L., Zhang, H., Cai, Z.: Dynamic k-nearest-neighbor naive bayes with attribute weighted. In: Proceedings of the 3rd International Conference on Fuzzy Systems and Knowledge Discovery, pp. 365–368. Springer (2006)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Harbin Institute of TechnologyHarbinChina
  2. 2.Communications Research CenterHarbin Institute of TechnologyHarbinChina

Personalised recommendations