Skip to content

Regression of large-scale path loss parameters using deep neural networks

Notifications You must be signed in to change notification settings

MstfBal/HeightMapPathLossPrediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 

Repository files navigation

HeightMapPathLossPrediction

Regression of large-scale path loss parameters using deep neural networks

Abstract

Path loss exponent and shadowing factor are among important wireless channel parameters. These parameters can be estimated using field measurements or ray-tracing simulations, which are costly and time-consuming. In this work, we take a deep neural network-based approach, which takes either satellite image or height map of a target region as input and estimates the desired channel parameters. We use the well-known VGG-16 architecture, pre-trained on the ImageNet dataset, as the backbone to extract image features, modify it as a regression network to produce channel parameters, and re-train it on our dataset, which consists of satellite image or height map as input and channel parameters as target values. We demonstrate that deep networks can be successfully utilized in estimating path loss exponent and shadowing factor of a region, simply from the region's satellite image or height map.

Method

The VGG-16 model is used for predicting path loss exponent component(n) and shadowing factor(σ).

Trained model weights and VGG-16 model are giving in this google drive link: https://drive.google.com/drive/folders/114YvDyYIZZs5nFH9Ff20K1Y7ejZLrnqc?usp=sharing

and the testing code can be found in this repo as jupyter-notebook file named as Testing_HeightMap.ipynb

github

Results

Prediction of path loss exponent and shadowing factor for test samples can be seen below.

githubresults

Authors Info

Mustafa BAL - mstfbal7@gmail.com

Ahmed Nageeb MAREY

Hasan Fehmi Ateş

Tuncer Baykaş

Bahadır K. Güntürk

Github stats 2

About

Regression of large-scale path loss parameters using deep neural networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published