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

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. Am-Drs 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 Neighbor (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.

On the Detection of Unauthorized Drones—Techniques and Future Perspectives: A Review

“…Using simple techniques such as cross correlation over PSD may not be very accurate; hence, authors in [37] propose the use of ML and more useful features including MFCC and Linear Predictive Cepstral Coefficients (LPCC). An extension of the work uses PSD, Root Mean Square (RMS) of the PSD, and MFCC extracted using Independent Component Analysis (ICA) and ML algorithms i.e., Support Vector Machine (SVM) [38] and K-Nearest Neighbors (KNN) [39] to detect drones [40]. A closely similar work propose the use of Independent Vector Analysis (IVA) for feature extraction from acoustic signals [41].…”

Counter-Unmanned Aircraft System(s) (C-UAS): State of the Art, Challenges and Future Trends

“…The UAS detection system can adjust the sensing algorithm accuracy to meet the requirement of detection once the abnormal signals are detected. In [91], the researchers leverage the unsupervised approaches to extract the features of signal from various acoustic sensors under different scenarios (bird, airplanes, thunderstorm, rain, wind and UAS). Based on the recognition of scenarios, the system, proposed in this research, triggers support vector machine (SVM) and K Nearest Neighbor (KNN), separately, to detect the amateur drones in the restricted areas.…”

“…9), can be classified into three categories: 1) Multiple-Sensor Data Fusion; 2) Multiple-Type Sensor Data Fusion; 3) Multiple Sensing Algorithm Fusion. Each sensor can record the audio and deliver the record to the ground stations to make a combination evaluation of the environment in sound spectrum [91]. The researchers extracted the phrase difference in the sound to locate the UAS.…”

Independent Vector Analysis Inspired Amateur Drone Detection Through Acoustic Signals

“…Thus, the technique developed in [13] is not practical feasible. In one of our previous paper, we developed an independent component analysis (ICA) [22], [23] based AmDrs detection technique [14] that is practically feasible and can detect multiple AmDrs at a time but inefficiency of ICA exist in the literature. The IVA technique [24] processes the actual recorded as well as delayed recorded signals that make it more practical as compare to ICA.…”