November 16, 2020

205 words 1 min read

lasseufpa/5gm-beam-selection

lasseufpa/5gm-beam-selection

Beam-selection for mmWave MIMO using machine learning

repo name lasseufpa/5gm-beam-selection
repo link https://github.com/lasseufpa/5gm-beam-selection
homepage
language Python
size (curr.) 33 kB
stars (curr.) 19
created 2018-04-06
license GNU General Public License v3.0

5GM BEAM SELECTION

Steps to run the code for ITA'2018 paper below. We are using Python 3.6.

  1. Git clone this repository

  2. Download datasets (for both classification and regression) avaliable at https://nextcloud.lasseufpa.org/s/jq3seNr5o8c8eQj and store the files in the folder datasets (for example: D:\github\5gm-beam-selection\datasets)

  3. Go to folder regression (for example, D:\github\5gm-beam-selection\regression) and execute:

python deep_convnet_regression.py

  1. Go to folder classification (for example, D:\github\5gm-beam-selection\classification) and execute:

python deep_ann_classifier.py

For more information on creating the dataset and related tasks, see the Wiki page at https://github.com/lasseufpa/5gm-data/wiki

Reference

If you use any data or code, please cite: “5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning”, Aldebaro Klautau, Pedro Batista, Nuria Gonzalez-Prelcic, Yuyang Wang and Robert W. Heath Jr., ITA'2018 (available at http://ita.ucsd.edu/workshop/18/files/paper/paper_3313.pdf).

Bibtex entry:
@inproceedings{Klautau18,
  author    = {Aldebaro Klautau and Pedro Batista and Nuria Gonzalez-Prelcic and Yuyang Wang and Robert W. {Heath Jr.}},
  title     = {{5G} {MIMO} Data for Machine Learning: Application to Beam-Selection using Deep Learning},
  booktitle = {2018 Information Theory and Applications Workshop, San Diego},
  pages     = {1--1},
  year      = {2018},
  url       = {http://ita.ucsd.edu/workshop/18/files/paper/paper_3313.pdf}
}
comments powered by Disqus