Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Drone Acoustic Analysis for Predicting Psychoacoustic Annoyance via Artificial Neural Networks

Andrea Vaiuso, Marcello Righi, Oier Coretti, Moreno Apicella

TL;DR

This study builds upon prior research by examining the efficacy of various Deep Learning models in predicting Psychoacoustic Annoyance, an effective index for measuring perceived annoyance by human ears, based on multiple drone characteristics as input by constructing a training dataset.

Abstract

Unmanned Aerial Vehicles (UAVs) have become widely used in various fields and industrial applications thanks to their low operational cost, compact size and wide accessibility. However, the noise generated by drone propellers has emerged as a significant concern. This may affect the public willingness to implement these vehicles in services that require operation in proximity to residential areas. The standard approaches to address this challenge include sound pressure measurements and noise characteristic analyses. The integration of Artificial Intelligence models in recent years has further streamlined the process by enhancing complex feature detection in drone acoustics data. This study builds upon prior research by examining the efficacy of various Deep Learning models in predicting Psychoacoustic Annoyance, an effective index for measuring perceived annoyance by human ears, based on multiple drone characteristics as input. This is accomplished by constructing a training dataset using precise measurements of various drone models with multiple microphones and analyzing flight data, maneuvers, drone physical characteristics, and perceived annoyance under realistic conditions. The aim of this research is to improve our understanding of drone noise, aid in the development of noise reduction techniques, and encourage the acceptance of drone usage on public spaces.

Drone Acoustic Analysis for Predicting Psychoacoustic Annoyance via Artificial Neural Networks

TL;DR

This study builds upon prior research by examining the efficacy of various Deep Learning models in predicting Psychoacoustic Annoyance, an effective index for measuring perceived annoyance by human ears, based on multiple drone characteristics as input by constructing a training dataset.

Abstract

Unmanned Aerial Vehicles (UAVs) have become widely used in various fields and industrial applications thanks to their low operational cost, compact size and wide accessibility. However, the noise generated by drone propellers has emerged as a significant concern. This may affect the public willingness to implement these vehicles in services that require operation in proximity to residential areas. The standard approaches to address this challenge include sound pressure measurements and noise characteristic analyses. The integration of Artificial Intelligence models in recent years has further streamlined the process by enhancing complex feature detection in drone acoustics data. This study builds upon prior research by examining the efficacy of various Deep Learning models in predicting Psychoacoustic Annoyance, an effective index for measuring perceived annoyance by human ears, based on multiple drone characteristics as input. This is accomplished by constructing a training dataset using precise measurements of various drone models with multiple microphones and analyzing flight data, maneuvers, drone physical characteristics, and perceived annoyance under realistic conditions. The aim of this research is to improve our understanding of drone noise, aid in the development of noise reduction techniques, and encourage the acceptance of drone usage on public spaces.

Paper Structure

This paper contains 18 sections, 4 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Featured works and goal
  3. Data Collection Methodology
  4. Drones selection and maneuver definition
  5. Microphone setup
  6. Measuring procedure
  7. Data analysis
  8. Acoustic spectra and spectrograms
  9. Sound Quality Metrics
  10. Psychoacoustic Annoyance
  11. Results
  12. Data prediction Methodology
  13. Feature Selection
  14. Model architecture
  15. Custom Validation
  16. ...and 3 more sections

Figures (10)

  • Figure 1: Final microphone setup. Each number represent the microphone ID.
  • Figure 2: (a) Microphone 2, 4, 6, 7 spectrum for DJI Matrice 300 RTK during hovering. (b) Microphone 2, 4, 6, 7 spectrum for DJI Mavic 2 Enterprise during hovering.
  • Figure 3: Comparison between (a) ground microphone spectrum versus (b) on-top microphone spectrum for DJI Matrice 300 RTK
  • Figure 4: Fourier transformed signals for all maneuvers for DJI Matrice 300 RTK.
  • Figure 5: Spectrograms for all maneuvers for DJI Matrice 300 RTK.
  • ...and 5 more figures