Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Receiver Operating Characteristic Plot01:15

Receiver Operating Characteristic Plot

322
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
322

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Noise reduction in brain magnetic resonance imaging using adaptive wavelet thresholding based on linear prediction factor.

Frontiers in neuroscience·2025
Same author

Automatic spread factor and position definition for UAV gateway through computational intelligence approach to maximize <i>signal-to-noise ratio</i> in wooded environments.

PeerJ. Computer science·2024
Same author

Application of Artificial Neural Networks for Prediction of Received Signal Strength Indication and Signal-to-Noise Ratio in Amazonian Wooded Environments.

Sensors (Basel, Switzerland)·2024
Same author

LoRa Technology Propagation Models for IoT Network Planning in the Amazon Regions.

Sensors (Basel, Switzerland)·2024
Same author

Intelligent Drone Positioning via BIC Optimization for Maximizing LPWAN Coverage and Capacity in Suburban Amazon Environments.

Sensors (Basel, Switzerland)·2023
Same author

Hybrid computational and real data-based positioning of small cells in 5G networks.

PeerJ. Computer science·2023

Related Experiment Video

Updated: Sep 3, 2025

Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
07:49

Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization

Published on: November 26, 2019

8.1K

SNR Prediction with ANN for UAV Applications in IoT Networks Based on Measurements.

Caio M M Cardoso1, Fabrício J B Barros1, Joel A R Carvalho1

  • 1Electrical Engineering Graduate Department, Federal University of Pará, Belém 66075-110, Brazil.

Sensors (Basel, Switzerland)
|July 27, 2022
PubMed
Summary

This study explored using Unmanned Aerial Vehicles (UAVs) with Long Range Wide-Area Networks (LoRaWAN) for 5G networks. Measurements in forests showed distinct communication behaviors, with a neural network accurately predicting signal-to-noise ratios.

Keywords:
LoRaartificial neural networkcommunication channeldensely woodedmeasurementssignal-to-noise ratio

More Related Videos

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem
10:15

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

3.8K
Calibration of Vector Network Analyzer for Measurements in Radio Frequency Propagation Channels
10:00

Calibration of Vector Network Analyzer for Measurements in Radio Frequency Propagation Channels

Published on: June 2, 2020

21.3K

Related Experiment Videos

Last Updated: Sep 3, 2025

Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
07:49

Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization

Published on: November 26, 2019

8.1K
Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem
10:15

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

3.8K
Calibration of Vector Network Analyzer for Measurements in Radio Frequency Propagation Channels
10:00

Calibration of Vector Network Analyzer for Measurements in Radio Frequency Propagation Channels

Published on: June 2, 2020

21.3K

Area of Science:

  • Wireless Communications
  • Network Engineering
  • Machine Learning Applications

Background:

  • Fifth-generation (5G) networks require enhanced coverage and capacity, particularly for massive machine-type communications (mMTC).
  • Unmanned Aerial Vehicles (UAVs) offer dynamic deployment for wireless infrastructure, acting as aerial base stations or relays.
  • Long Range Wide-Area Network (LoRaWAN) is a key technology for low-power, wide-area IoT applications, aligning with 5G mMTC goals.

Purpose of the Study:

  • To investigate the synergistic potential of integrating UAVs with LoRaWAN for 5G wireless networks.
  • To analyze the performance of LoRa communication links at various UAV altitudes and spreading factors in challenging environments.
  • To develop and evaluate a neural network model for predicting signal-to-noise ratio (SNR) in LoRa-UAV communication scenarios.

Main Methods:

  • Conducted extensive measurement campaigns in suburban and densely forested environments to capture real-world LoRa-UAV link behavior.
  • Evaluated both downlink and uplink LoRa communication performance across different UAV heights and spreading factors (SF).
  • Trained a neural network to predict measured SNR values and compared its accuracy against traditional SNR regression models.

Main Results:

  • Distinct communication performance patterns were observed for LoRa links at varying UAV altitudes and SFs in both uplink and downlink.
  • The trained neural network demonstrated high accuracy in predicting SNR, with Root Mean Square Error (RMSE) below 1.67 dB for downlink.
  • For uplink communication, the neural network achieved even higher precision, with RMSE values below 1.39 dB and standard deviation below 1.18 dB.

Conclusions:

  • UAV-assisted LoRaWAN presents a viable solution for enhancing 5G wireless network coverage and supporting mMTC.
  • The study validates the effectiveness of a neural network approach for modeling and predicting complex wireless channel behavior in LoRa-UAV systems.
  • Accurate SNR prediction using machine learning can optimize resource allocation and network performance in future 5G deployments.