<div> <div> <div> <p>This paper introduced a near real-time acoustic unmanned aerial vehicle detection system with multiple listening nodes using machine learning models. An audio dataset was collected in person by recording the sound of an unmanned aerial vehicle flying around as well as the sound of background noises. After the data collection phase, support vector machines and convolutional neural networks were built with two features, Mel-frequency cepstral coefficients and short-time Fourier transform. Considering the near real-time environment, the features were calculated after cutting the audio stream into chunks of two, one or half seconds. There are four combinations of features and models as well as three versions per combination based on the chunk size, returning twelve models in total. To train support vector machines, the exhaustive search method was used to find the best parameter while convolutional neural networks were built by selecting the parameters manually. Four node configurations were devised to find the best way to place six listening nodes. Twelve models were run for each configuration, generating color maps to show the paths of the unmanned aerial vehicle flying along the nodes. The model of short-time Fourier transform and support vector machines showed the path most clearly with the least false negatives with 2-second chunk size. Among the four configurations, the configuration for experiment 3 showed the best results in terms of the distance of detection results on the color maps. Web-based monitoring dashboards were provided to enable users to monitor detection results. </p> </div> </div> </div>

Counter Unmanned Aerial System (CUAS) security systems have unrealistic performance expectations hyped on marketing and idealistic testing environments. By developing an agent-based model to simulate these systems, an average performance metric can be obtained, thereby providing better representative values of true system performance.<br><br>Due to high cost, excessive risk, and exponentially large parameter possibilities, it is unrealistic to test a CUAS system for optimal performance in the real world. Agent-based simulation can provide the necessary variability at a low cost point and allow for numerous parametric possibilities to provide actionable output from the CUAS system. <br><br>This study describes and documents the Simulation of CUAS Networks and Sensors (SCANS) Framework in a novel attempt at developing a flexible modeling framework for CUAS systems based on device parameters. The core of the framework rests on sensor and communication device agents. These sensors, including Acoustic, Radar, Passive Radio Frequency (RF), and Camera, use input parameters, sensor specifications, and UAS specifications to calculate such values as the sound pressure level, received signal strength, and maximum viewable distance. The communication devices employ a nearest-neighbor routing protocol to pass messages from the system which are then logged by a command and control agent. <br><br>This framework allows for the flexibility of modeling nearly any CUAS system and is designed to be easily adjusted. The framework is capable of reporting true positives, true negatives, and false negatives in terms of UAS detection. For testing purposes, the SCANS Framework was deployed in AnyLogic and models were developed based on existing, published, empirical studies of sensors and detection UAS.<br>