Amateur Drones Detection : A machine learning approach utilizing the acoustic signals in the presence of strong interference

Uddin, Zahoor and Altaf, Muhammad and Bilal, Muhammad and Nkenyereye, Lewis and Bashir, Ali Kashif (2020) Amateur Drones Detection : A machine learning approach utilizing the acoustic signals in the presence of strong interference. Computer Communications, 154. pp. 236-245. ISSN 0140-3664

Abstract

Owing to small size, sensing capabilities and autonomous nature, the Unmanned Air Vehicles (UAVs) have enormous applications in various areas e.g., remote sensing, navigation, archaeology, journalism, environmental science, and agriculture. However, the un-monitored deployment of UAVs called the amateur drones (AmDr) can lead to serious security threats and risk to human life and infrastructure. Therefore, timely detection of the AmDr is essential for the protection and security of sensitive organizations, human life and other vital infrastructure. AmDrs can be detected using different techniques based on sound, video, thermal, and radio frequencies. However, the performance of these techniques is limited in sever atmospheric conditions. In this paper, we propose an efficient un-supervise machine learning approach of independent component analysis (ICA) to detect various acoustic signals i.e., sounds of bird, airplanes, thunderstorm, rain, wind and the UAVs in practical scenario. After unmixing the signals, the features like Mel Frequency Cepstral Coefficients (MFCC), the power spectral density (PSD) and the Root Mean Square Value (RMS) of the PSD are extracted by using ICA. The PSD and the RMS of PSD signals are extracted by first passing the signals from octave band filter banks. Based on the above features the signals are classified using Support Vector Machines (SVM)and K Nearest Neighbour (KNN)to detect the presence or absence of AmDr. Unique feature of the proposed technique is the detection of a single or multiple AmDrs at a time in the presence of multiple acoustic interfering signals. The proposed technique is verified through extensive simulations and it is observed that the RMS values of PSD with KNN performs better than the MFCC with KNN and SVM.