Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dataset of Pathloss and ToA Radio Maps With Localization Application

Çağkan Yapar, Ron Levie, Gitta Kutyniok, Giuseppe Caire

TL;DR

A collection of radio map datasets in dense urban setting, which is generated and made publicly available and includes simulated pathloss/received signal strength (RSS) and time of arrival (ToA) radio maps over a large collection of realistic dense urbanSetting in real city maps.

Abstract

In this article, we present a collection of radio map datasets in dense urban setting, which we generated and made publicly available. The datasets include simulated pathloss/received signal strength (RSS) and time of arrival (ToA) radio maps over a large collection of realistic dense urban setting in real city maps. The two main applications of the presented dataset are 1) learning methods that predict the pathloss from input city maps (namely, deep learning-based simulations), and, 2) wireless localization. The fact that the RSS and ToA maps are computed by the same simulations over the same city maps allows for a fair comparison of the RSS and ToA-based localization methods.

Dataset of Pathloss and ToA Radio Maps With Localization Application

TL;DR

A collection of radio map datasets in dense urban setting, which is generated and made publicly available and includes simulated pathloss/received signal strength (RSS) and time of arrival (ToA) radio maps over a large collection of realistic dense urbanSetting in real city maps.

Abstract

In this article, we present a collection of radio map datasets in dense urban setting, which we generated and made publicly available. The datasets include simulated pathloss/received signal strength (RSS) and time of arrival (ToA) radio maps over a large collection of realistic dense urban setting in real city maps. The two main applications of the presented dataset are 1) learning methods that predict the pathloss from input city maps (namely, deep learning-based simulations), and, 2) wireless localization. The fact that the RSS and ToA maps are computed by the same simulations over the same city maps allows for a fair comparison of the RSS and ToA-based localization methods.
Paper Structure (12 sections, 4 figures, 2 tables)

This paper contains 12 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. General Setting
  3. 2D Datasets
  4. 2D Radio Map Versions with Cars
  5. The RadioMapSeer Dataset
  6. Additional Higher Accuracy 2D Pathloss Radio Map Datasets
  7. Datasets Specialized for Localization
  8. RadioLocSeer Dataset
  9. RadioToASeer Dataset
  10. The RadioMap3DSeer Dataset
  11. Determining the Radio Map Truncation Values
  12. On the (Quasi) Optimality of the ToA Dataset

Figures (4)

  • Figure 1: A visual overview of the presented datasets and their application in localization. Shown are: City maps w/o and w/ height encoding, roads and cars, pathloss radio map prediction and simulation under different settings, and the result of a localization experiment with LocUNet LocUNetTWC.
  • Figure 2: A simulated map from the presented 3D pathloss radio map dataset. The rays arriving at a chosen pixel are shown. Tx mounted on the rooftop of a high building
  • Figure 3: An example application of the 3D dataset. Shown are the height-encoded city map and the Tx (red plus sign), 3D radio map from the dataset, and the radio map predictions by the naive and the 3D adapted RadioUNet RadioUNetTWC variants.
  • Figure 4: Empirical CDF of the difference between the direct and dominant path in meters.