A Feature Engineering Focused System for Acoustic UAV Detection

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.