Path Loss Modeling for mmWave for Urban Scenarios Using Meta-Learning and 3D Images 


Vol. 46,  No. 12, pp. 2229-2236, Dec.  2021
10.7840/kics.2021.46.12.2229


PDF
  Abstract

An accurate and efficient pathloss prediction modeling method for mmWave communication plays an important role in the successful introduction of mmWave-based 5G mobile communication systems. Existing methods often suffer from limitations in practical application due to low accuracy and efficiency compared to the requirements for base station settings of deployment sites, especially in dense urban environments. In this paper, we propose a mmWave pathloss modeling method for dense urban environment based on deep learning, which has attracted much attention recently, and an input image generation algorithm based on 3D map data. The proposed model training algorithm is based on meta-learning which can secure high prediction accuracy even when a sufficient amount of training data is unavailable. The experimental results show a superior performance over the CNN models trained by using 2D input images and 3D input images without meta-learning.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

W. Jin, H. Kim, H. Lee, "Path Loss Modeling for mmWave for Urban Scenarios Using Meta-Learning and 3D Images," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 12, pp. 2229-2236, 2021. DOI: 10.7840/kics.2021.46.12.2229.

[ACM Style]

Woobeen Jin, Hyeonjin Kim, and Hyukjoon Lee. 2021. Path Loss Modeling for mmWave for Urban Scenarios Using Meta-Learning and 3D Images. The Journal of Korean Institute of Communications and Information Sciences, 46, 12, (2021), 2229-2236. DOI: 10.7840/kics.2021.46.12.2229.

[KICS Style]

Woobeen Jin, Hyeonjin Kim, Hyukjoon Lee, "Path Loss Modeling for mmWave for Urban Scenarios Using Meta-Learning and 3D Images," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 12, pp. 2229-2236, 12. 2021. (https://doi.org/10.7840/kics.2021.46.12.2229)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880