A Feature Engineering Focused System for Acoustic UAV Detection
Authors:
- 1 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 125-130
Abstract
The evolution of Unmanned Aerial Vehicles (UAVs) technology has made these devices suitable for a wide new range of applications, but it has also raised safety concerns as UAVs can be used for carrying explosives or weapons with malicious intentions. In this paper, Machine Learning (ML) algorithms are used to identify UAVs by using the sound signals they emit. We evaluate and propose a feature-based classification. Five individual features, and one combination of features are used to train four machine learning classification approaches: a neural network (NN), a support vector machine (SVM), a Gaussian Naive Bayes (GNB), and K-Nearest Neighbor (KNN). The training and testing dataset is composed of sound samples of UAVs and noise. The labels in the dataset we collected include the sound files of noise and UAVs. The results show that the combination of features outperforms the individual ones, with higher average accuracy scores.Keywords
This publication has 17 references indexed in Scilit:
- Using deep networks for drone detection2017
- A study on detecting drones using deep convolutional neural networks2017
- Digital television based passive bistatic radar system for drone detection2017
- Real-time UAV sound detection and analysis system2017
- Drone detection by acoustic signature identificationElectronic Imaging, 2017
- Classification of Birds and UAVs Based on Radar PolarimetryIEEE Geoscience and Remote Sensing Letters, 2016
- Investigating Cost-effective RF-based Detection of Drones2016
- Detecting Flying Objects Using a Single Moving CameraIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- 35 GHz FMCW drone detection system2016
- Drone sound detection2015